Tootfinder

from my link log —
NaN-propagation: a novel method for sparsity detection in black-box computational functions.
https://arxiv.org/abs/2507.23186
saved 2025-08-14

NaN-Propagation: A Novel Method for Sparsity Detection in Black-Box Computational Functions
When numerically evaluating a function's gradient, sparsity detection can enable substantial computational speedups through Jacobian coloring and compression. However, sparsity detection techniques for black-box functions are limited, and existing finite-difference-based methods suffer from false negatives due to coincidental zero gradients. These false negatives can silently corrupt gradient calculations, leading to difficult-to-diagnose errors. We introduce NaN-propagation, which exploits the…

Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers
Andrei Chertkov, Artem Basharin, Mikhail Saygin, Evgeny Frolov, Stanislav Straupe, Ivan Oseledets
https://arxiv.org/abs/2509.15113

Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers
The growing demand for energy-efficient, high-performance AI systems has led to increased attention on alternative computing platforms (e.g., photonic, neuromorphic) due to their potential to accelerate learning and inference. However, integrating such physical components into deep learning pipelines remains challenging, as physical devices often offer limited expressiveness, and their non-differentiable nature renders on-device backpropagation difficult or infeasible. This motivates the develo…

CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
Boyu Zhang, Ping He, Tianyu Du, Xuhong Zhang, Lei Yun, Kingsum Chow, Jianwei Yin
https://arxiv.org/abs/2509.13982

CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code LM to protect its IP, they have limitations when facing the more practical and complex demand, i.e., offering the individual user-level tracing in the black-box setting. This work presents CLMTracing, a black-box code LM watermarking framework employing the rul…

Another day of job interviews here at @… research group. Tea of the day: Watanabe Yutaka Midori Shincha 2024
#teaoftheday #greentea

🇺🇦 #NowPlaying on KEXP's #VarietyMix
Open Mike Eagle:
🎵 my co‐worker clark kent’s secret black box
#OpenMikeEagle
https://open.spotify.com/track/4l8t27aV3hDR55Dv7Nx7UX

Sample-Constrained Black Box Optimization for Audio Personalization
Rajalaxmi Rajagopalan, Yu-Lin Wei, Romit Roy Choudhury
https://arxiv.org/abs/2507.12773

Sample-Constrained Black Box Optimization for Audio Personalization
We consider the problem of personalizing audio to maximize user experience. Briefly, we aim to find a filter $h^*$, which applied to any music or speech, will maximize the user's satisfaction. This is a black-box optimization problem since the user's satisfaction function is unknown. Substantive work has been done on this topic where the key idea is to play audio samples to the user, each shaped by a different filter $h_i$, and query the user for their satisfaction scores $f(h_i)$. A family of …

Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
Shilian Chen, Jie Zhou, Tianyu Huai, Yujiang Lu, Junsong Li, Bihao Zhan, Qianjun Pan, Yutao Yang, Xin Li, Qin Chen, Hang Yan, Liang He
https://arxiv.org/abs/2509.12951

Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
Model merging refers to the process of integrating multiple distinct models into a unified model that preserves and combines the strengths and capabilities of the individual models. Most existing approaches rely on task vectors to combine models, typically under the assumption that model parameters are accessible. However, for extremely large language models (LLMs) such as GPT-4, which are often provided solely as black-box services through API interfaces (Language-Model-as-a-Service), model we…

« To the extent that we are stuck for now with untrustworthy LLMs that nobody can quite control, rapidly enshittifying the internet with botshit and replacing humans with systems that can’t be relied on, it is in part because we have spent too much energy pursuing the pure neural net black box approach, and not enough into looking at alternatives. We are drowning in a sea of mediocre prose precisely because LLMs, the backbone of virtually all current sytems, lack the underlying representatio…

How o3 and Grok 4 Accidentally Vindicated Neurosymbolic AI
Neurosymbolic AI is quietly winning. Here’s what that means – and why it took so long

MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
Weiwei Qi, Shuo Shao, Wei Gu, Tianhang Zheng, Puning Zhao, Zhan Qin, Kui Ren
https://arxiv.org/abs/2508.13048

MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
Large Language Models (LLMs) have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating the input prompts. Existing black-box jailbreaking techniques primarily rely on static prompts crafted with a single, non-adaptive strategy, or employ rigid combinations of several underperforming attack methods, which limits their adaptability and generalization. To address these limitations, we propose MAJIC, a Mark…

Generative Co-Design of Antibody Sequences and Structures via Black-Box Guidance in a Shared Latent Space
Yinghua Yao, Yuangang Pan, Xixian Chen
https://arxiv.org/abs/2508.11424

Generative Co-Design of Antibody Sequences and Structures via Black-Box Guidance in a Shared Latent Space
Advancements in deep generative models have enabled the joint modeling of antibody sequence and structure, given the antigen-antibody complex as context. However, existing approaches for optimizing complementarity-determining regions (CDRs) to improve developability properties operate in the raw data space, leading to excessively costly evaluations due to the inefficient search process. To address this, we propose LatEnt blAck-box Design (LEAD), a sequence-structure co-design framework that opt…

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models
Jiaxuan Zhao, Naibin Gu, Yuchen Feng, Xiyu Liu, Peng Fu, Zheng Lin, Weiping Wang
https://arxiv.org/abs/2509.12112

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models
The high costs of customizing large language models (LLMs) fundamentally limit their adaptability to user-specific needs. Consequently, LLMs are increasingly offered as cloud-based services, a paradigm that introduces critical limitations: providers struggle to support personalized customization at scale, while users face privacy risks when exposing sensitive data. To address this dual challenge, we propose Customized Black-box Prompt Tuning (CBP-Tuning), a novel framework that facilitates effi…

TailO-RAN: O-RAN Control on Scheduler Parameters to Tailor RAN Performance
Nicolo Longhi, Salvatore D'Oro, Leonardo Bonati, Michele Polese, Roberto Verdone, Tommaso Melodia
https://arxiv.org/abs/2508.12112

TailO-RAN: O-RAN Control on Scheduler Parameters to Tailor RAN Performance
The traditional black-box and monolithic approach to Radio Access Networks (RANs) has heavily limited flexibility and innovation. The Open RAN paradigm, and the architecture proposed by the O-RAN ALLIANCE, aim to address these limitations via openness, virtualization and network intelligence. In this work, first we propose a novel, programmable scheduler design for Open RAN Distributed Units (DUs) that can guarantee minimum throughput levels to User Equipments (UEs) via configurable weights. Th…

A Hierarchical Surrogate Model for Efficient Multi-Task Parameter Learning in Closed-Loop Contro
Sebastian Hirt, Lukas Theiner, Maik Pfefferkorn, Rolf Findeisen
https://arxiv.org/abs/2508.12738

A Hierarchical Surrogate Model for Efficient Multi-Task Parameter Learning in Closed-Loop Contro
Many control problems require repeated tuning and adaptation of controllers across distinct closed-loop tasks, where data efficiency and adaptability are critical. We propose a hierarchical Bayesian optimization (BO) framework that is tailored to efficient controller parameter learning in sequential decision-making and control scenarios for distinct tasks. Instead of treating the closed-loop cost as a black-box, our method exploits structural knowledge of the underlying problem, consisting of a…

An Efficient Network-aware Direct Search Method for Influence Maximization
Matteo Bergamaschi, Sara Venturini, Francesco Tudisco, Francesco Rinaldi
https://arxiv.org/abs/2508.12164

An Efficient Network-aware Direct Search Method for Influence Maximization
Influence Maximization (IM) is a pivotal concept in social network analysis, involving the identification of influential nodes within a network to maximize the number of influenced nodes, and has a wide variety of applications that range from viral marketing and information dissemination to public health campaigns. IM can be modeled as a combinatorial optimization problem with a black-box objective function, where the goal is to select $B$ seed nodes that maximize the expected influence spread.…

ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings
Rehan Raza, Guanjin Wang, Kevin Wong, Hamid Laga, Marco Fisichella
https://arxiv.org/abs/2508.13672

ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings
Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior locally using interpretable surrogate models. However, LIME's inherent randomness in perturbation and sampling can lead to locality and instability issues, especially in scenarios with limited training data. In such cases, data scarcity can result in the generation of unrealistic…

🦾 AI tool targets RNA structures to unravel secrets of the dark genome
#rna

AI tool targets RNA structures to unravel secrets of the dark genome
We mapped the human genome decades ago, but most of it is still a black box. Now, UNSW scientists have developed a tool to peer inside and what they find could reshape how we think about disease.

Kickstarted a credit-card-sized dice replacement.
For IRL D&D it was fine, but dials spin forever. Made dice tray pointless, while less satisfying. Even though I choose yellow text on black, hard for me to see in mood-lit basement on table
For Shadowrun, 6D6 is embarrassingly insufficient, given I regularly roll 14D6. The VTT roller is far better (since it does the math on pools and successes).
But they’re sturdy and hefty! Which means my mini metal dice are lighter an…

ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization
Shengzhuang Chen, Xu Ouyang, Michael Arthur Leopold Pearce, Thomas Hartvigsen, Jonathan Richard Schwarz
https://arxiv.org/abs/2508.11551

ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization
Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no learning-based approach has emerged as a reliable solution. In this work, we propose to view the selection of training data mixtures as a black-box hyperparameter optimization problem, for which Bayesian Optimization is a well-established class of appropriate algorith…

Discrete optimal transport is a strong audio adversarial attack
Anton Selitskiy, Akib Shahriyar, Jishnuraj Prakasan
https://arxiv.org/abs/2509.14959 https://

Discrete optimal transport is a strong audio adversarial attack
In this paper, we show that discrete optimal transport (DOT) is an effective black-box adversarial attack against modern audio anti-spoofing countermeasures (CMs). Our attack operates as a post-processing, distribution-alignment step: frame-level WavLM embeddings of generated speech are aligned to an unpaired bona fide pool via entropic OT and a top-$k$ barycentric projection, then decoded with a neural vocoder. Evaluated on ASVspoof2019 and ASVspoof5 with AASIST baselines, DOT yields consisten…

Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing
Ruicheng Xian, Yuxuan Wan, Han Zhao
https://arxiv.org/abs/2508.11258 https://

Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing
Instruction fine-tuned large language models (LLMs) enable a simple zero-shot or few-shot prompting paradigm, also known as in-context learning, for building prediction models. This convenience, combined with continued advances in LLM capability, has the potential to drive their adoption across a broad range of domains, including high-stakes applications where group fairness -- preventing disparate impacts across demographic groups -- is essential. The majority of existing approaches to enforci…

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
Wenqiang Wang, Yan Xiao, Hao Lin, Yangshijie Zhang, Xiaochun Cao
https://arxiv.org/abs/2508.10039 ht…

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attacks are less effective against practical scenarios involving black-box feedback APIs, limited queries, or multiple task types. To bridge this gap, we propose \textbf{C}luster and \textbf{E}nsemble \textbf{M}ulti-task Text Adversarial \textbf{A}ttack (\textbf{CEMA}), an effective black-box attack that exploits the transf…

Role-Augmented Intent-Driven Generative Search Engine Optimization
Xiaolu Chen, Haojie Wu, Jie Bao, Zhen Chen, Yong Liao, Hu Huang
https://arxiv.org/abs/2508.11158 https://

Role-Augmented Intent-Driven Generative Search Engine Optimization
Generative Search Engines (GSEs), powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), are reshaping information retrieval. While commercial systems (e.g., BingChat, Perplexity.ai) demonstrate impressive semantic synthesis capabilities, their black-box nature fundamentally undermines established Search Engine Optimization (SEO) practices. Content creators face a critical challenge: their optimization strategies, effective in traditional search engines, are misaligne…

Deploying UDM Series in Real-Life Stuttered Speech Applications: A Clinical Evaluation Framework
Eric Zhang (SSHealth Team, AI for Healthcare Laboratory), Li Wei (SSHealth Team, AI for Healthcare Laboratory), Sarah Chen (SSHealth Team, AI for Healthcare Laboratory), Michael Wang (SSHealth Team, AI for Healthcare Laboratory)
https://arxiv.o…

Deploying UDM Series in Real-Life Stuttered Speech Applications: A Clinical Evaluation Framework
Stuttered and dysfluent speech detection systems have traditionally suffered from the trade-off between accuracy and clinical interpretability. While end-to-end deep learning models achieve high performance, their black-box nature limits clinical adoption. This paper looks at the Unconstrained Dysfluency Modeling (UDM) series-the current state-of-the-art framework developed by Berkeley that combines modular architecture, explicit phoneme alignment, and interpretable outputs for real-world clini…

Polynomial Optimization via Random Projection and Consensus
Etienne Buehrle, Christoph Stiller
https://arxiv.org/abs/2509.12859 https://arxiv.org/pdf/2509.…

Polynomial Optimization via Random Projection and Consensus
We propose a black-box approach to reducing large semidefinite programs to a set of smaller semidefinite programs by projecting to random linear subspaces. We evaluate our method on a set of polynomial optimization problems, demonstrating improved scalability.

Model Interpretability and Rationale Extraction by Input Mask Optimization
Marc Brinner, Sina Zarriess
https://arxiv.org/abs/2508.11388 https://arxiv.org/p…

Model Interpretability and Rationale Extraction by Input Mask Optimization
Concurrent to the rapid progress in the development of neural-network based models in areas like natural language processing and computer vision, the need for creating explanations for the predictions of these black-box models has risen steadily. We propose a new method to generate extractive explanations for predictions made by neural networks, that is based on masking parts of the input which the model does not consider to be indicative of the respective class. The masking is done using gradi…

Large Language Model-assisted Meta-optimizer for Automated Design of Constrained Evolutionary Algorithm
Xu Yang, Rui Wang, Kaiwen Li, Wenhua Li, Weixiong Huang
https://arxiv.org/abs/2509.13251

Large Language Model-assisted Meta-optimizer for Automated Design of Constrained Evolutionary Algorithm
Meta-black-box optimization has been significantly advanced through the use of large language models (LLMs), yet in fancy on constrained evolutionary optimization. In this work, AwesomeDE is proposed that leverages LLMs as the strategy of meta-optimizer to generate update rules for constrained evolutionary algorithm without human intervention. On the meanwhile, $RTO^2H$ framework is introduced for standardize prompt design of LLMs. The meta-optimizer is trained on a diverse set of constrained o…

AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models
Rebecca Martin, Jay Patrikar, Sebastian Scherer
https://arxiv.org/abs/2509.08638 https://

AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models
Specialized machine learning models, regardless of architecture and training, are susceptible to failures in deployment. With their increasing use in high risk situations, the ability to audit these models by determining their operational design domain (ODD) is crucial in ensuring safety and compliance. However, given the high-dimensional input spaces, this process often requires significant human resources and domain expertise. To alleviate this, we introduce \coolname, an LLM-Agent centric fr…

Urban Solitude IV 🈳
城市孤独 IV 🈳
📷 Pentax MX
🎞️Fujifilm Neopan SS, expired 1995
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Yiding Cao Geld mit PayPal.Me senden
Folgen Sie dem Link PayPal.Me/dingsterdingster und geben Sie den Betrag ein. Es ist bequem und sicher. Sie haben noch kein PayPal-Konto? Kein Problem.

Good film... but OMG my son lost his everlovin' mind watching 'A #Minecraft Movie', screaming at not just the 'Chicken Jockey' but also the 'music', 'mods', YouTubers, 'Alex' & more.
✅ ‘A Minecraft Movie’ Ends Its Theatrical Run. How Much Did It Make?

‘A Minecraft Movie’ Ends Its Theatrical Run. How Much Did It Make?
Jack Black and Jason Momoa’s “A Minecraft Movie” has officially wrapped up its run in theaters. How much money did it make at the box office?

Deep opacity and AI: A threat to XAI and to privacy protection mechanisms
Vincent C. M\"uller
https://arxiv.org/abs/2509.08835 https://arxiv.org/pdf/2…

Deep opacity and AI: A threat to XAI and to privacy protection mechanisms
It is known that big data analytics and AI pose a threat to privacy, and that some of this is due to some kind of "black box problem" in AI. I explain how this becomes a problem in the context of justification for judgments and actions. Furthermore, I suggest distinguishing three kinds of opacity: 1) the subjects do not know what the system does ("shallow opacity"), 2) the analysts do not know what the system does ("standard black box opacity"), or 3) the analysts cannot possibly know what the …

Global Optimization of Stochastic Black-Box Functions with Arbitrary Noise Distributions using Wilson Score Kernel Density Estimation
Thorbj{\o}rn Mosekj{\ae}r Iversen, Lars Car{\o}e S{\o}rensen, Simon Faarvang Mathiesen, Henrik Gordon Petersen
https://arxiv.org/abs/2509.09238

Global Optimization of Stochastic Black-Box Functions with Arbitrary Noise Distributions using Wilson Score Kernel Density Estimation
Many optimization problems in robotics involve the optimization of time-expensive black-box functions, such as those involving complex simulations or evaluation of real-world experiments. Furthermore, these functions are often stochastic as repeated experiments are subject to unmeasurable disturbances. Bayesian optimization can be used to optimize such methods in an efficient manner by deploying a probabilistic function estimator to estimate with a given confidence so that regions of the search…

Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
Edward Phillips, Sean Wu, Soheila Molaei, Danielle Belgrave, Anshul Thakur, David Clifton
https://arxiv.org/abs/2509.13813

Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
Large language models demonstrate impressive results across diverse tasks but are still known to hallucinate, generating linguistically plausible but incorrect answers to questions. Uncertainty quantification has been proposed as a strategy for hallucination detection, but no existing black-box approach provides estimates for both global and local uncertainty. The former attributes uncertainty to a batch of responses, while the latter attributes uncertainty to individual responses. Current loca…

Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae
Stav Armoni-Friedmann, Hana Chockler, David A. Kelly
https://arxiv.org/abs/2509.09982 https:/…

Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae
Evaluating explainable AI (XAI) approaches is a challenging task in general, due to the subjectivity of explanations. In this paper, we focus on tabular data and the specific use case of AI models predicting the values of Boolean functions. We extend the previous work in this domain by proposing a formal and precise measure of importance of variables based on actual causality, and we evaluate state-of-the-art XAI tools against this measure. We also present a novel XAI tool B-ReX, based on the e…

A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality
Rongqian Chen, Allison Andreyev, Yanming Xiu, Mahdi Imani, Bin Li, Maria Gorlatova, Gang Tan, Tian Lan
https://arxiv.org/abs/2508.09185

A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality
Augmented Reality (AR) enriches perception by overlaying virtual elements on the physical world. Due to its growing popularity, cognitive attacks that alter AR content to manipulate users' semantic perception have received increasing attention. Existing detection methods often focus on visual changes, which are restricted to pixel- or image-level processing and lack semantic reasoning capabilities, or they rely on pre-trained vision-language models (VLMs), which function as black-box approaches…

On the Convergence of Large Language Model Optimizer for Black-Box Network Management
Hoon Lee, Wentao Zhou, Merouane Debbah, Inkyu Lee
https://arxiv.org/abs/2507.02689

On the Convergence of Large Language Model Optimizer for Black-Box Network Management
Future wireless networks are expected to incorporate diverse services that often lack general mathematical models. To address such black-box network management tasks, the large language model (LLM) optimizer framework, which leverages pretrained LLMs as optimization agents, has recently been promoted as a promising solution. This framework utilizes natural language prompts describing the given optimization problems along with past solutions generated by LLMs themselves. As a result, LLMs can ob…

Side view of a decorated electric box inspired by the anime となりのトトロ (My Neighbor Totoro)
#photo #photography #ithaca #art

Black-Box Bug-Amplification for Multithreaded Software
Yeshayahu Weiss, Gal Amram, Achiya Elyasaf, Eitan Farchi, Oded Margalit, Gera Weiss
https://arxiv.org/abs/2507.21318 https…

Black-Box Bug-Amplification for Multithreaded Software
Bugs, especially those in concurrent systems, are often hard to reproduce because they manifest only under rare conditions. Testers frequently encounter failures that occur only under specific inputs, even when occurring with low probability. We propose an approach to systematically amplify the occurrence of such elusive bugs. We treat the system under test as a black-box and use repeated trial executions to train a predictive model that estimates the probability of a given input configuration …

Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
Baolei Zhang, Haoran Xin, Yuxi Chen, Zhuqing Liu, Biao Yi, Tong Li, Lihai Nie, Zheli Liu, Minghong Fang
https://arxiv.org/abs/2509.13772

Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) integrates external knowledge into large language models to improve response quality. However, recent work has shown that RAG systems are highly vulnerable to poisoning attacks, where malicious texts are inserted into the knowledge database to influence model outputs. While several defenses have been proposed, they are often circumvented by more adaptive or sophisticated attacks. This paper presents RAGOrigin, a black-box responsibility attribution framewo…

Floating-Body Hydrodynamic Neural Networks
Tianshuo Zhang, Wenzhe Zhai, Rui Yann, Jia Gao, He Cao, Xianglei Xing
https://arxiv.org/abs/2509.13783 https://a…

Floating-Body Hydrodynamic Neural Networks
Fluid-structure interaction is common in engineering and natural systems, where floating-body motion is governed by added mass, drag, and background flows. Modeling these dissipative dynamics is difficult: black-box neural models regress state derivatives with limited interpretability and unstable long-horizon predictions. We propose Floating-Body Hydrodynamic Neural Networks (FHNN), a physics-structured framework that predicts interpretable hydrodynamic parameters such as directional added mas…

Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control
Anton Klenitskiy, Konstantin Polev, Daria Denisova, Alexey Vasilev, Dmitry Simakov, Gleb Gusev
https://arxiv.org/abs/2507.12202

Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control
Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their internals can help understand, influence, and control their behavior, which is very important in a variety of real-world applications. Recently sparse autoencoders (SAE) have been shown to be a promising unsupervised approach for extracting interpretable features f…

Subsampling Factorization Machine Annealing
Yusuke Hama, Tadashi Kadowaki
https://arxiv.org/abs/2508.08778 https://arxiv.org/pdf/2508.08778

Subsampling Factorization Machine Annealing
Quantum computing and machine learning are state-of-the-art technologies which have been investigated intensively in both academia and industry. The hybrid technology of these two ingredients is expected to be a powerful tool to solve complex problems in many branches of science and engineering such as combinatorial optimization problems and accelerate the creation of next-generation technologies. In this work, we develop an algorithm to solve a black-box optimization problem by improving Facto…

Swarm Intelligence for Chemical Reaction Optimisation
R\'emi Schlama, Joshua W. Sin, Ryan P. Burwood, Kurt P\"untener, Raphael Bigler, Philippe Schwaller
https://arxiv.org/abs/2509.11798

Swarm Intelligence for Chemical Reaction Optimisation
Chemical reaction optimisation is essential for synthetic chemistry and pharmaceutical development, demanding the extensive exploration of many reaction parameters to achieve efficient and sustainable processes. We report $α$-PSO, a novel nature-inspired metaheuristic algorithm that augments canonical particle swarm optimisation (PSO) with machine learning (ML) for parallel reaction optimisation. Unlike black-box ML approaches that obscure decision-making processes, $α$-PSO uses mechanistical…

Replaced article(s) found for cs.CC. https://arxiv.org/list/cs.CC/new
[1/1]:
- Black-Box Identity Testing of Noncommutative Rational Formulas in Deterministic Quasipolynomial Time
V. Arvind, Abhranil Chatterjee, Partha Mukhopadhyay

From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms
Zhaokun Jiang, Ziyin Zhang
https://arxiv.org/abs/2508.10860

From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms
Recent advancements in machine learning have spurred growing interests in automated interpreting quality assessment. Nevertheless, existing research suffers from insufficient examination of language use quality, unsatisfactory modeling effectiveness due to data scarcity and imbalance, and a lack of efforts to explain model predictions. To address these gaps, we propose a multi-dimensional modeling framework that integrates feature engineering, data augmentation, and explainable machine learning…

Componentwise Automata Learning for System Integration (Extended Version)
Hiroya Fujinami, Masaki Waga, Jie An, Kohei Suenaga, Nayuta Yanagisawa, Hiroki Iseri, Ichiro Hasuo
https://arxiv.org/abs/2508.04458

Componentwise Automata Learning for System Integration (Extended Version)
Compositional automata learning is attracting attention as an analysis technique for complex black-box systems. It exploits a target system's internal compositional structure to reduce complexity. In this paper, we identify system integration -- the process of building a new system as a composite of potentially third-party and black-box components -- as a new application domain of compositional automata learning. Accordingly, we propose a new problem setting, where the learner has direct access…

To buy or not to buy: deterministic rent-or-buy problems on node-weighted graphs
Sander Borst, Moritz Venzin
https://arxiv.org/abs/2507.08698 https://

To buy or not to buy: deterministic rent-or-buy problems on node-weighted graphs
We study the rent-or-buy variant of the online Steiner forest problem on node- and edge-weighted graphs. For $n$-node graphs with at most $\bar{n}$ non-zero node-weights, and at most $\tilde{k}$ different arriving terminal pairs, we obtain a deterministic, $O(\log n \log \bar{n})$-competitive algorithm. This improves on the previous best, $O(\log^4 n)$-competitive algorithm obtained by the black-box reduction from (Bartal et al. 2021) combined with the previously best deterministic algorithms f…

Observations from the Seattle Seahawks Press Box After 23-23 Raiders Tie https://www.si.com/nfl/raiders/las-vegas-seattle-seahawks-podcast-pete-carroll-chip-kelly-gen0-smith-cam-miller

TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Ziming Wei, Zichen Kong, Yuan Wang, David Z. Pan, Xiyuan Tang
https://arxiv.org/abs/2509.14169

TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Analog and mixed-signal circuit design remains challenging due to the shortage of high-quality data and the difficulty of embedding domain knowledge into automated flows. Traditional black-box optimization achieves sampling efficiency but lacks circuit understanding, which often causes evaluations to be wasted in low-value regions of the design space. In contrast, learning-based methods embed structural knowledge but are case-specific and costly to retrain. Recent attempts with large language m…

🇺🇦 #NowPlaying on KEXP's #AfternoonShow
Open Mike Eagle:
🎵 my co-worker clark kent's secret black box
#OpenMikeEagle
https://openmikeeagle.bandcamp.com/track/my-co-worker-clark-kents-secret-black-box
https://open.spotify.com/track/4l8t27aV3hDR55Dv7Nx7UX

The current bane of my life. Those who know what this is, know my pain.

Sampling as Bandits: Evaluation-Efficient Design for Black-Box Densities
Takuo Matsubara, Andrew Duncan, Simon Cotter, Konstantinos Zygalakis
https://arxiv.org/abs/2509.01437 ht…

Sampling as Bandits: Evaluation-Efficient Design for Black-Box Densities
We introduce bandit importance sampling (BIS), a new class of importance sampling methods designed for settings where the target density is expensive to evaluate. In contrast to adaptive importance sampling, which optimises a proposal distribution, BIS directly designs the samples through a sequential strategy that combines space-filling designs with multi-armed bandits. Our method leverages Gaussian process surrogates to guide sample selection, enabling efficient exploration of the parameter s…

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
Chiyu Zhang, Lu Zhou, Xiaogang Xu, Jiafei Wu, Liming Fang, Zhe Liu
https://arxiv.org/abs/2508.10390 https:…

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
Evaluating jailbreak attacks is challenging when prompts are not overtly harmful or fail to induce harmful outputs. Unfortunately, many existing red-teaming datasets contain such unsuitable prompts. To evaluate attacks accurately, these datasets need to be assessed and cleaned for maliciousness. However, existing malicious content detection methods rely on either manual annotation, which is labor-intensive, or large language models (LLMs), which have inconsistent accuracy in harmful types. To b…

If you need me, I'll be in my office.

Synthesis of Deep Neural Networks with Safe Robust Adaptive Control for Reliable Operation of Wheeled Mobile Robots
Mehdi Heydari Shahna, Jouni Mattila
https://arxiv.org/abs/2508.10634

Synthesis of Deep Neural Networks with Safe Robust Adaptive Control for Reliable Operation of Wheeled Mobile Robots
Deep neural networks (DNNs) can enable precise control while maintaining low computational costs by circumventing the need for dynamic modeling. However, the deployment of such black-box approaches remains challenging for heavy-duty wheeled mobile robots (WMRs), which are subject to strict international standards and prone to faults and disturbances. We designed a hierarchical control policy for heavy-duty WMRs, monitored by two safety layers with differing levels of authority. To this end, a D…

Today has been mainly about stripping down my favourite mountain bike for repainting and renovation.
#BikeTooter

So arguably the Pac-Man ghost logic is the exact opposite of “AI”.
It’s extremely well defined behavior based on very basic deterministic algorithms that are so simple a 8-year old player can understand them and anticipate them correctly for those high-scores.
The game actually is famous for the simple enemy logic and studied by games designers for it.
Pac-Man enemy behavior:
deterministic, well-defined algorithm that can easily be executed on the most primitive* computer hardware
“AI”:
black-box algorithm with indeterministic behavior that requires a metric shitload of compute
—
*By “primitive computer hardware” I mean that the Pac-Man arcade machine runs on a Zilog Z80 CPU with 8,500 transistors.The CPU in the phone you are reading this on has (latest iPhone as example) 15 billion transistors or so (almost 2 million times more) and runs tens of thousands of times faster.

Black-box optimization using factorization and Ising machines
Ryo Tamura, Yuya Seki, Yuki Minamoto, Koki Kitai, Yoshiki Matsuda, Shu Tanaka, Koji Tsuda
https://arxiv.org/abs/2507.18003

Black-box optimization using factorization and Ising machines
Black-box optimization (BBO) is used in materials design, drug discovery, and hyperparameter tuning in machine learning. The world is experiencing several of these problems. In this review, a factorization machine with quantum annealing or with quadratic-optimization annealing (FMQA) algorithm to realize fast computations of BBO using Ising machines (IMs) is discussed. The FMQA algorithm uses a factorization machine (FM) as a surrogate model for BBO. The FM model can be directly transformed int…

Control Analysis and Design for Autonomous Vehicles Subject to Imperfect AI-Based Perception
Tao Yan, Zheyu Zhang, Jingjing Jiang, Wen-Hua Chen
https://arxiv.org/abs/2509.12137 …

Control Analysis and Design for Autonomous Vehicles Subject to Imperfect AI-Based Perception
Safety is a critical concern in autonomous vehicle (AV) systems, especially when AI-based sensing and perception modules are involved. However, due to the black box nature of AI algorithms, it makes closed-loop analysis and synthesis particularly challenging, for example, establishing closed-loop stability and ensuring performance, while they are fundamental to AV safety. To approach this difficulty, this paper aims to develop new modeling, analysis, and synthesis tools for AI-based AVs. Inspir…

aivi & surasshu make my fav background music when reading
#music

Transparent and Fair Profiling in Employment Services: Evidence from Switzerland
Tim R\"az
https://arxiv.org/abs/2509.11847 https://arxiv.org/pdf/2509…

Transparent and Fair Profiling in Employment Services: Evidence from Switzerland
Long-term unemployment (LTU) is a challenge for both jobseekers and public employment services. Statistical profiling tools are increasingly used to predict LTU risk. Some profiling tools are opaque, black-box machine learning models, which raise issues of transparency and fairness. This paper investigates whether interpretable models could serve as an alternative, using administrative data from Switzerland. Traditional statistical, interpretable, and black-box models are compared in terms of p…

Urban Snaps 📸
城市抓拍 📸
📷 Pentax MX
🎞️Fujifilm Neopan SS, expired 1995
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Yiding Cao Geld mit PayPal.Me senden
Folgen Sie dem Link PayPal.Me/dingsterdingster und geben Sie den Betrag ein. Es ist bequem und sicher. Sie haben noch kein PayPal-Konto? Kein Problem.

Multi-Sensory Cognitive Computing for Learning Population-level Brain Connectivity
Mayssa Soussia, Mohamed Ali Mahjoub, Islem Rekik
https://arxiv.org/abs/2508.11436 https://

Multi-Sensory Cognitive Computing for Learning Population-level Brain Connectivity
The generation of connectional brain templates (CBTs) has recently garnered significant attention for its potential to identify unique connectivity patterns shared across individuals. However, existing methods for CBT learning such as conventional machine learning and graph neural networks (GNNs) are hindered by several limitations. These include: (i) poor interpretability due to their black-box nature, (ii) high computational cost, and (iii) an exclusive focus on structure and topology, overlo…

JustEva: A Toolkit to Evaluate LLM Fairness in Legal Knowledge Inference
Zongyue Xue, Siyuan Zheng, Shaochun Wang, Yiran Hu, Shenran Wang, Yuxin Yao, Haitao Li, Qingyao Ai, Yiqun Liu, Yun Liu, Weixing Shen
https://arxiv.org/abs/2509.12104

JustEva: A Toolkit to Evaluate LLM Fairness in Legal Knowledge Inference
The integration of Large Language Models (LLMs) into legal practice raises pressing concerns about judicial fairness, particularly due to the nature of their "black-box" processes. This study introduces JustEva, a comprehensive, open-source evaluation toolkit designed to measure LLM fairness in legal tasks. JustEva features several advantages: (1) a structured label system covering 65 extra-legal factors; (2) three core fairness metrics - inconsistency, bias, and imbalanced inaccuracy; (3) robu…

🇺🇦 #NowPlaying on KEXP's #VarietyMix
Black Box:
🎵 Everybody Everybody
#BlackBox
https://edit-mix.bandcamp.com/track/black-box-everybody-everybody-hot-mix-118-bpm
https://open.spotify.com/track/6wBMTv8yTiNh50fqTkT0JC

Efficient optimization of expensive black-box simulators via marginal means, with application to neutrino detector design
Hwanwoo Kim, Simon Mak, Ann-Kathrin Schuetz, Alan Poon
https://arxiv.org/abs/2508.01834

Efficient optimization of expensive black-box simulators via marginal means, with application to neutrino detector design
With advances in scientific computing, computer experiments are increasingly used for optimizing complex systems. However, for modern applications, e.g., the optimization of nuclear physics detectors, each experiment run can require hundreds of CPU hours, making the optimization of its black-box simulator over a high-dimensional space a challenging task. Given limited runs at inputs $\mathbf{x}_1, \cdots, \mathbf{x}_n$, the best solution from these evaluated inputs can be far from optimal, part…

Trust-region Filter Algorithms utilising Hessian Information for Grey-Box Optimisation
Gul Hameed, Tao Chen, Antonio del Rio Chanona, Lorenz T. Biegler, Michael Short
https://arxiv.org/abs/2509.01651

Trust-region Filter Algorithms utilising Hessian Information for Grey-Box Optimisation
Optimising industrial processes is essential for enhancing profitability, efficiency, and sustainability. Conventional optimisation relies on equation-oriented (EO) glass-box models with fully specified equations and accessible derivatives. However, many real-world systems contain black-box components (such as high-fidelity computational fluid dynamics simulators or proprietary unit models) that lack explicit formulations or analytic gradients. This limits the applicability of derivative-based …

Feature Space Analysis by Guided Diffusion Model
Kimiaki Shirahama, Miki Yanobu, Kaduki Yamashita, Miho Ohsaki
https://arxiv.org/abs/2509.07936 https://arx…

Feature Space Analysis by Guided Diffusion Model
One of the key issues in Deep Neural Networks (DNNs) is the black-box nature of their internal feature extraction process. Targeting vision-related domains, this paper focuses on analysing the feature space of a DNN by proposing a decoder that can generate images whose features are guaranteed to closely match a user-specified feature. Owing to this guarantee that is missed in past studies, our decoder allows us to evidence which of various attributes in an image are encoded into a feature by th…

BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS
Ye Li, Chengcheng Zhu, Yanchao Zhao, Jiale Zhang
https://arxiv.org/abs/2508.03307 https://

BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS
In this paper, we endeavor to address the challenges of backdoor attacks countermeasures in black-box scenarios, thereby fortifying the security of inference under MLaaS. We first categorize backdoor triggers from a new perspective, i.e., their impact on the patched area, and divide them into: high-visibility triggers (HVT), semi-visibility triggers (SVT), and low-visibility triggers (LVT). Based on this classification, we propose a progressive defense framework, BDFirewall, that removes these …

Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
Kamel Kamel, Hridoy Sankar Dutta, Keshav Sood, Sunil Aryal
https://arxiv.org/abs/2509.07677

Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
Voice Authentication Systems (VAS) use unique vocal characteristics for verification. They are increasingly integrated into high-security sectors such as banking and healthcare. Despite their improvements using deep learning, they face severe vulnerabilities from sophisticated threats like deepfakes and adversarial attacks. The emergence of realistic voice cloning complicates detection, as systems struggle to distinguish authentic from synthetic audio. While anti-spoofing countermeasures (CMs) …

Sound Matching an Analogue Levelling Amplifier Using the Newton-Raphson Method
Chin-Yun Yu, Gy\"orgy Fazekas
https://arxiv.org/abs/2509.10706 https://…

Sound Matching an Analogue Levelling Amplifier Using the Newton-Raphson Method
Automatic differentiation through digital signal processing algorithms for virtual analogue modelling has recently gained popularity. These algorithms are typically more computationally efficient than black-box neural networks that rely on dense matrix multiplications. Due to their differentiable nature, they can be integrated with neural networks and jointly trained using gradient descent algorithms, resulting in more efficient systems. Furthermore, signal processing algorithms have significan…

Solving Markov Chains with Analog Quantum Computing: The Fine Print
Ward van der Schoot, Niels M. P. Neumann
https://arxiv.org/abs/2508.02199 https://arxiv…

Solving Markov Chains with Analog Quantum Computing: The Fine Print
With a growing interest in quantum computing, the number of proposed quantum algorithms grows as well. The practical applicability of these algorithms differs: Some can be applied out-of-the-box, while others require black box oracles, which can not always be easily implemented. One of the first works to explicitly discuss these practical applicability aspects is by Aaronson discussing the \textit{fine print} of the HHL quantum algorithm that solves linear systems of equations. We extend this l…

Cost-aware Stopping for Bayesian Optimization
Qian Xie, Linda Cai, Alexander Terenin, Peter I. Frazier, Ziv Scully
https://arxiv.org/abs/2507.12453 https:/…

Cost-aware Stopping for Bayesian Optimization
In automated machine learning, scientific discovery, and other applications of Bayesian optimization, deciding when to stop evaluating expensive black-box functions is an important practical consideration. While several adaptive stopping rules have been proposed, in the cost-aware setting they lack guarantees ensuring they stop before incurring excessive function evaluation costs. We propose a cost-aware stopping rule for Bayesian optimization that adapts to varying evaluation costs and is free…

Scalable Synthesis and Verification of String Stable Neural Certificates for Interconnected Systems
Jingyuan Zhou, Haoze Wu, Haokun Yu, Kaidi Yang
https://arxiv.org/abs/2509.10118

Scalable Synthesis and Verification of String Stable Neural Certificates for Interconnected Systems
Ensuring string stability is critical for the safety and efficiency of large-scale interconnected systems. Although learning-based controllers (e.g., those based on reinforcement learning) have demonstrated strong performance in complex control scenarios, their black-box nature hinders formal guarantees of string stability. To address this gap, we propose a novel verification and synthesis framework that integrates discrete-time scalable input-to-state stability (sISS) with neural network verif…

PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray Reasoning
Yushi Feng, Junye Du, Yingying Hong, Qifan Wang, Lequan Yu
https://arxiv.org/abs/2508.10501

PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray Reasoning
Existing tool-augmented agentic systems are limited in the real world by (i) black-box reasoning steps that undermine trust of decision-making and pose safety risks, (ii) poor multimodal integration, which is inherently critical for healthcare tasks, and (iii) rigid and computationally inefficient agentic pipelines. We introduce PASS (Probabilistic Agentic Supernet Sampling), the first multimodal framework to address these challenges in the context of Chest X-Ray (CXR) reasoning. PASS adaptivel…

👊 Building my own paper tape punch
#hardware #technology

Risk Map As Middleware: Towards Interpretable Cooperative End-to-end Autonomous Driving for Risk-Aware Planning
Mingyue Lei, Zewei Zhou, Hongchen Li, Jiaqi Ma, Jia Hu
https://arxiv.org/abs/2508.07686

Risk Map As Middleware: Towards Interpretable Cooperative End-to-end Autonomous Driving for Risk-Aware Planning
End-to-end paradigm has emerged as a promising approach to autonomous driving. However, existing single-agent end-to-end pipelines are often constrained by occlusion and limited perception range, resulting in hazardous driving. Furthermore, their black-box nature prevents the interpretability of the driving behavior, leading to an untrustworthiness system. To address these limitations, we introduce Risk Map as Middleware (RiskMM) and propose an interpretable cooperative end-to-end driving frame…

A linesearch-based derivative-free method for noisy black-box problems
Alberto De Santis, Giampaolo Liuzzi, Stefano Lucidi
https://arxiv.org/abs/2508.00495 https://

A linesearch-based derivative-free method for noisy black-box problems
In this work we consider unconstrained optimization problems. The objective function is known through a zeroth order stochastic oracle that gives an estimate of the true objective function. To solve these problems, we propose a derivative-free algorithm based on extrapolation techniques. Under reasonable assumptions we are able to prove convergence properties for the proposed algorithms. Furthermore, we also give a worst-case complexity result stating that the total number of iterations where t…

Uneven Lives VII 👁️
不工整人生 VII 👁️
📷 Minolta Hi-Matic AF
🎞️ERA 100, expired 1994
#filmphotography #Photography #blackandwhite

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
Minghui Li, Hao Zhang, Yechao Zhang, Wei Wan, Shengshan Hu, pei Xiaobing, Jing Wang
https://arxiv.org/abs/2509.07617

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and the poor transferability of black-box methods, we propose an activations-guided prompt injection attack framework. We first construct an Energy-based Model (EBM) using activations from a surrogate model to evaluate the quality of adversarial prompts. Guided b…

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
Huizhen Shu, Xuying Li, Qirui Wang, Yuji Kosuga, Mengqiu Tian, Zhuo Li
https://arxiv.org/abs/2508.10404

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challenge for understanding model vulnerabilities and improving robustness. In this context, we propose a new black-box attack method that leverages the interpretability of large models. We introduce the Sparse Feature Perturbation Framework (SFPF), a novel approach for adversarial text generation that utilizes sparse autoenc…

Wild refitting for black box prediction
Martin J. Wainwright
https://arxiv.org/abs/2506.21460 https://arxiv.org/pdf/2506.21460…

Wild refitting for black box prediction
We describe and analyze a computionally efficient refitting procedure for computing high-probability upper bounds on the instance-wise mean-squared prediction error of penalized nonparametric estimates based on least-squares minimization. Requiring only a single dataset and black box access to the prediction method, it consists of three steps: computing suitable residuals, symmetrizing and scaling them with a pre-factor $ρ$, and using them to define and solve a modified prediction problem rece…

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
Zhengxian Wu, Juan Wen, Wanli Peng, Haowei Chang, Yinghan Zhou, Yiming Xue
https://arxiv.org/abs/2508.06153

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
With the development of customized large language model (LLM) agents, a new threat of black-box backdoor attacks has emerged, where malicious instructions are injected into hidden system prompts. These attacks easily bypass existing defenses that rely on white-box access, posing a serious security challenge. To address this, we propose SLIP, a Soft Label mechanism and key-extraction-guided CoT-based defense against Instruction backdoors in APIs. SLIP is designed based on two key insights. First…

Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment
Sascha Kaltenpoth, Oliver M\"uller
https://arxiv.org/abs/2509.07642

Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment
Adopting Large language models (LLMs) in organizations potentially revolutionizes our lives and work. However, they can generate off-topic, discriminating, or harmful content. This AI alignment problem often stems from misspecifications during the LLM adoption, unnoticed by the principal due to the LLM's black-box nature. While various research disciplines investigated AI alignment, they neither address the information asymmetries between organizational adopters and black-box LLM agents nor con…

AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
Sangjun Lee, Seung-taek Woo, Jungyu Jin, Changhun Lee, Eunhyeok Park
https://arxiv.org/abs/2509.12019

AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
To enable broader deployment of Large Language Models (LLMs), it is essential to identify the best-performing model under strict memory constraints. We present AMQ, Automated Mixed-Precision Weight-Only Quantization, a framework that assigns layer-wise quantization bit-widths to optimally balance model quality and memory usage. However, the combinatorial search space, with over 10^{100} possible configurations, makes conventional black-box optimization infeasible. AMQ overcomes this challenge t…

A Zeroth-Order Extra-Gradient Method For Black-Box Constrained Optimization
Yuke Zhou, Ruiyang Jin, Siyang Gao, Jianxiao Wang, Jie Song
https://arxiv.org/abs/2506.20546

A Zeroth-Order Extra-Gradient Method For Black-Box Constrained Optimization
Non-analytical objectives and constraints often arise in control systems, particularly in problems with complex dynamics, which are challenging yet lack efficient solution methods. In this work, we consider general constrained optimization problems involving black-box objectives and constraints. To solve it, we reformulate it as a min-max problem and propose a zeroth-order extra gradient (ZOEG) algorithm that combines the extra gradient method with a feedback-based stochastic zeroth-order gradi…

Investigating Advanced Reasoning of Large Language Models via Black-Box Interaction
Congchi Yin, Tianyi Wu, Yankai Shu, Alex Gu, Yunhan Wang, Jun Shao, Xun Jiang, Piji Li
https://arxiv.org/abs/2508.19035

Investigating Advanced Reasoning of Large Language Models via Black-Box Interaction
Existing tasks fall short in evaluating reasoning ability of Large Language Models (LLMs) in an interactive, unknown environment. This deficiency leads to the isolated assessment of deductive, inductive, and abductive reasoning, neglecting the integrated reasoning process that is indispensable for humans discovery of real world. We introduce a novel evaluation paradigm, \textit{black-box interaction}, to tackle this challenge. A black-box is defined by a hidden function that maps a specific set…

MAIA: An Inpainting-Based Approach for Music Adversarial Attacks
Yuxuan Liu, Peihong Zhang, Rui Sang, Zhixin Li, Shengchen Li
https://arxiv.org/abs/2509.04980 https://

MAIA: An Inpainting-Based Approach for Music Adversarial Attacks
Music adversarial attacks have garnered significant interest in the field of Music Information Retrieval (MIR). In this paper, we present Music Adversarial Inpainting Attack (MAIA), a novel adversarial attack framework that supports both white-box and black-box attack scenarios. MAIA begins with an importance analysis to identify critical audio segments, which are then targeted for modification. Utilizing generative inpainting models, these segments are reconstructed with guidance from the outp…

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation
Kanchon Gharami, Hansaka Aluvihare, Shafika Showkat Moni, Berker Pek\"oz
https://arxiv.org/abs/2509.00973

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation
Large Language Models (LLMs) are increasingly deployed in mission-critical systems, facilitating tasks such as satellite operations, command-and-control, military decision support, and cyber defense. Many of these systems are accessed through application programming interfaces (APIs). When such APIs lack robust access controls, they can expose full or top-k logits, creating a significant and often overlooked attack surface. Prior art has mainly focused on reconstructing the output projection la…

Tree-Structured Parzen Estimator Can Solve Black-Box Combinatorial Optimization More Efficiently
Kenshin Abe, Yunzhuo Wang, Shuhei Watanabe
https://arxiv.org/abs/2507.08053 https://arxiv.org/pdf/2507.08053 https://arxiv.org/html/2507.08053
arXiv:2507.08053v1 Announce Type: new
Abstract: Tree-structured Parzen estimator (TPE) is a versatile hyperparameter optimization (HPO) method supported by popular HPO tools. Since these HPO tools have been developed in line with the trend of deep learning (DL), the problem setups often used in the DL domain have been discussed for TPE such as multi-objective optimization and multi-fidelity optimization. However, the practical applications of HPO are not limited to DL, and black-box combinatorial optimization is actively utilized in some domains, e.g., chemistry and biology. As combinatorial optimization has been an untouched, yet very important, topic in TPE, we propose an efficient combinatorial optimization algorithm for TPE. In this paper, we first generalize the categorical kernel with the numerical kernel in TPE, enabling us to introduce a distance structure to the categorical kernel. Then we discuss modifications for the newly developed kernel to handle a large combinatorial search space. These modifications reduce the time complexity of the kernel calculation with respect to the size of a combinatorial search space. In the experiments using synthetic problems, we verified that our proposed method identifies better solutions with fewer evaluations than the original TPE. Our algorithm is available in Optuna, an open-source framework for HPO.
toXiv_bot_toot

Beyond the Black Box: Integrating Lexical and Semantic Methods in Quantitative Discourse Analysis with BERTopic
Thomas Compton
https://arxiv.org/abs/2508.19099 https://

Beyond the Black Box: Integrating Lexical and Semantic Methods in Quantitative Discourse Analysis with BERTopic
Quantitative Discourse Analysis has seen growing adoption with the rise of Large Language Models and computational tools. However, reliance on black box software such as MAXQDA and NVivo risks undermining methodological transparency and alignment with research goals. This paper presents a hybrid, transparent framework for QDA that combines lexical and semantic methods to enable triangulation, reproducibility, and interpretability. Drawing from a case study in historical political discourse, we …

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
Biao Yi, Tiansheng Huang, Sishuo Chen, Tong Li, Zheli Liu, Zhixuan Chu, Yiming Li
https://arxiv.org/abs/2506.16447

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of LLMs in the real-world Large Language Model as a Service (LLMaaS) setting, where the deployed model is a fully black-box system that can only interact through text. Furthermore, the sample-dependent nature of the attack target exacerbates the threat. Instead …

Rethinking the Privacy of Text Embeddings: A Reproducibility Study of "Text Embeddings Reveal (Almost) As Much As Text"
Dominykas Seputis, Yongkang Li, Karsten Langerak, Serghei Mihailov
https://arxiv.org/abs/2507.07700

Rethinking the Privacy of Text Embeddings: A Reproducibility Study of "Text Embeddings Reveal (Almost) As Much As Text"
Text embeddings are fundamental to many natural language processing (NLP) tasks, extensively applied in domains such as recommendation systems and information retrieval (IR). Traditionally, transmitting embeddings instead of raw text has been seen as privacy-preserving. However, recent methods such as Vec2Text challenge this assumption by demonstrating that controlled decoding can successfully reconstruct original texts from black-box embeddings. The unexpectedly strong results reported by Vec2…

Sequentially Auditing Differential Privacy
Tom\'as Gonz\'alez, Mateo Dulce-Rubio, Aaditya Ramdas, M\'onica Ribero
https://arxiv.org/abs/2509.07055 https://

Sequentially Auditing Differential Privacy
We propose a practical sequential test for auditing differential privacy guarantees of black-box mechanisms. The test processes streams of mechanisms' outputs providing anytime-valid inference while controlling Type I error, overcoming the fixed sample size limitation of previous batch auditing methods. Experiments show this test detects violations with sample sizes that are orders of magnitude smaller than existing methods, reducing this number from 50K to a few hundred examples, across divers…

Breaking the Black Box: Inherently Interpretable Physics-Informed Machine Learning for Imbalanced Seismic Data
Vemula Sreenath, Filippo Gatti, Pierre Jehel
https://arxiv.org/abs/2508.19031

Breaking the Black Box: Inherently Interpretable Physics-Informed Machine Learning for Imbalanced Seismic Data
Ground motion models (GMMs) predict how strongly the ground will shake during an earthquake. They are essential for structural analysis, seismic design, and seismic risk assessment studies. Traditional machine learning (ML) approaches are popular to develop GMMs, due to large earthquake databases worldwide. However, they operate as "black boxes," which are hard to interpret and trust, limiting their use in high-stake decisions. Additionally, these databases suffer from significant data imbalanc…

Instance-level Performance Prediction for Long-form Generation Tasks
Chi-Yang Hsu, Alexander Braylan, Yiheng Su, Omar Alonso, Matthew Lease
https://arxiv.org/abs/2509.07309 http…

Instance-level Performance Prediction for Long-form Generation Tasks
We motivate and share a new benchmark for instance-level performance prediction of long-form generation tasks having multi-faceted, fine-grained quality metrics. Our task-, model- and metric-agnostic formulation predicts continuous evaluation metric scores given only black-box model inputs and outputs. Beyond predicting point estimates of metric scores, the benchmark also requires inferring prediction intervals to quantify uncertainty around point estimates. Evaluation spans 11 long-form datase…

ProvX: Generating Counterfactual-Driven Attack Explanations for Provenance-Based Detection
Weiheng Wu, Wei Qiao, Teng Li, Yebo Feng, Zhuo Ma, Jianfeng Ma, Yang Liu
https://arxiv.org/abs/2508.06073

ProvX: Generating Counterfactual-Driven Attack Explanations for Provenance-Based Detection
Provenance graph-based intrusion detection systems are deployed on hosts to defend against increasingly severe Advanced Persistent Threat. Using Graph Neural Networks to detect these threats has become a research focus and has demonstrated exceptional performance. However, the widespread adoption of GNN-based security models is limited by their inherent black-box nature, as they fail to provide security analysts with any verifiable explanations for model predictions or any evidence regarding th…

Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
Zhicheng Zhang, Peizhuo Lv, Mengke Wan, Jiang Fang, Diandian Guo, Yezeng Chen, Yinlong Liu, Wei Ma, Jiyan Sun, Liru Geng
https://arxiv.org/abs/2507.20650

Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
Recently, Deep Learning (DL) models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property (IP) risks, as models are distributed on numerous local devices, making them vulnerable to theft and redistribution. Most existing ownership protection solutions (e.g., backdoor-based watermarking) are designed for cloud-based AI-as-a-Service (AIaaS) and are not directly applicab…

Graph-based Integrated Gradients for Explaining Graph Neural Networks
Lachlan Simpson, Kyle Millar, Adriel Cheng, Cheng-Chew Lim, Hong Gunn Chew
https://arxiv.org/abs/2509.07648

Graph-based Integrated Gradients for Explaining Graph Neural Networks
Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work, we introduce graph-based integrated gradients (GB-IG); an extension of IG to graphs. We demonstrate on four synthetic datasets that GB-IG accurately identifies crucial structural components of the graph used in classification tasks. We further demonstrate on t…

Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
Haonan An, Guang Hua, Hangcheng Cao, Zhengru Fang, Guowen Xu, Susanto Rahardja, Yuguang Fang
https://arxiv.org/abs/2507.18034

Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
The intellectual property of deep generative networks (GNets) can be protected using a cascaded hiding network (HNet) which embeds watermarks (or marks) into GNet outputs, known as box-free watermarking. Although both GNet and HNet are encapsulated in a black box (called operation network, or ONet), with only the generated and marked outputs from HNet being released to end users and deemed secure, in this paper, we reveal an overlooked vulnerability in such systems. Specifically, we show that t…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/5]:
- Wild refitting for black box prediction
Martin J. Wainwright
…