Tootfinder

Fluffy kitty vs 7 very happy void puppies

Makary denies plans for COVID-19 black box warning (Joseph Choi/The Hill)
https://thehill.com/policy/healthcare/5651857-fda-denies-black-box-warning-covid19/
http://www.memeorandum.com/251216/p134#a251216p134

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

"In a world beset by war, genocide, systemic discrimination, and climate catastrophe, we need good news. Donyelle McCray offers the opportunity to hear and see the embodiment of good news emanating from marginalized voices—especially Black women, laypeople, artists, and activists."
From the Christian Century review of the new book by YDS professor Donyelle McCray, "Is it a Sermon?"

Preaching outside the box
Donyelle McCray takes readers on a tour of the edges of homiletics, exploring Black Americans’ gospel proclamation in various...

Have you fucking tried asking people if they're in pain and not using a black-box biased phrenology algorithm that will only give white males the necessary meds

Latent-Feature-Informed Neural ODE Modeling for Lightweight Stability Evaluation of Black-box Grid-Tied Inverters
Jialin Zheng, Zhong Liu, Xiaonan Lu
https://arxiv.org/abs/2510.09826

Latent-Feature-Informed Neural ODE Modeling for Lightweight Stability Evaluation of Black-box Grid-Tied Inverters
Stability evaluation of black-box grid-tied inverters is vital for grid reliability, yet identification techniques are both data-hungry and blocked by proprietary internals. {To solve this, this letter proposes a latent-feature-informed neural ordinary differential equation (LFI-NODE) modeling method that can achieve lightweight stability evaluation directly from trajectory data.} LFI-NODE parameterizes the entire system ODE with a single continuous-time neural network, allowing each new sample…

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

I actually only needed some small light in order to be able to identify things in the dark box in low light conditions.
Somehow, that escalated quickly and turned into some #Christmas thing. 😎
Just two 7€ xmas LED sets with a 3xAA battery pack each.
#muli

A Black-Box Debiasing Framework for Conditional Sampling
Han Cui, Jingbo Liu
https://arxiv.org/abs/2510.11071 https://arxiv.org/pdf/2510.11071

A Black-Box Debiasing Framework for Conditional Sampling
Conditional sampling is a fundamental task in Bayesian statistics and generative modeling. Consider the problem of sampling from the posterior distribution $P_{X|Y=y^*}$ for some observation $y^*$, where the likelihood $P_{Y|X}$ is known, and we are given $n$ i.i.d. samples $D=\{X_i\}_{i=1}^n$ drawn from an unknown prior distribution $π_X$. Suppose that $f(\hatπ_{X^n})$ is the distribution of a posterior sample generated by an algorithm (e.g. a conditional generative model or the Ba…

Verifying Chain-of-Thought Reasoning via Its Computational Graph
Zheng Zhao, Yeskendir Koishekenov, Xianjun Yang, Naila Murray, Nicola Cancedda
https://arxiv.org/abs/2510.09312 …

Verifying Chain-of-Thought Reasoning via Its Computational Graph
Current Chain-of-Thought (CoT) verification methods predict reasoning correctness based on outputs (black-box) or activations (gray-box), but offer limited insight into why a computation fails. We introduce a white-box method: Circuit-based Reasoning Verification (CRV). We hypothesize that attribution graphs of correct CoT steps, viewed as execution traces of the model's latent reasoning circuits, possess distinct structural fingerprints from those of incorrect steps. By training a classifier o…

ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization
Jamison Meindl, Yunsheng Tian, Tony Cui, Veronika Thost, Zhang-Wei Hong, Johannes D\"urholt, Jie Chen, Wojciech Matusik, Mina Konakovi\'c Lukovi\'c
https://arxiv.org/abs/2510.03051

ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization
Global optimization of expensive, derivative-free black-box functions requires extreme sample efficiency. While Bayesian optimization (BO) is the current state-of-the-art, its performance hinges on surrogate and acquisition function hyper-parameters that are often hand-tuned and fail to generalize across problem landscapes. We present ZeroShotOpt, a general-purpose, pretrained model for continuous black-box optimization tasks ranging from 2D to 20D. Our approach leverages offline reinforcement …

Accelerated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models
Chih-Yu Chang, Ming-Chung Chang
https://arxiv.org/abs/2510.08465 https://

Accelerated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models
Recent advances in supervised learning have driven growing interest in explaining black-box models, particularly by estimating the effects of input variables on model predictions. However, existing approaches often face key limitations, including poor scalability, sensitivity to out-of-distribution sampling, and instability under correlated features. To address these issues, we propose A2D2E, an $\textbf{E}$stimator based on $\textbf{A}$ccelerated $\textbf{A}$ggregated $\textbf{D}$-Optimal $\te…

Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
Shuo Shao, Yiming Li, Hongwei Yao, Yifei Chen, Yuchen Yang, Zhan Qin
https://arxiv.org/abs/2510.06605

Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
The substantial investment required to develop Large Language Models (LLMs) makes them valuable intellectual property, raising significant concerns about copyright protection. LLM fingerprinting has emerged as a key technique to address this, which aims to verify a model's origin by extracting an intrinsic, unique signature (a "fingerprint") and comparing it to that of a source model to identify illicit copies. However, existing black-box fingerprinting methods often fail to generate distinctiv…

ZQBA: Zero Query Black-box Adversarial Attack
Joana C. Costa, Tiago Roxo, Hugo Proen\c{c}a, Pedro R. M. In\'acio
https://arxiv.org/abs/2510.00769 https://

ZQBA: Zero Query Black-box Adversarial Attack
Current black-box adversarial attacks either require multiple queries or diffusion models to produce adversarial samples that can impair the target model performance. However, these methods require training a surrogate loss or diffusion models to produce adversarial samples, which limits their applicability in real-world settings. Thus, we propose a Zero Query Black-box Adversarial (ZQBA) attack that exploits the representations of Deep Neural Networks (DNNs) to fool other networks. Instead of …

Moody Urbanity - Relations 👥
情绪化城市 - 关系 👥
📷 Minolta Hi-Matic AF
🎞️ Shanghai GP3 400 Pan
#filmphotography #Photography #blackandwhite

Proton: an incredible feat of software engineering; a Rube Goldberg machine that brought Windows gaming to Linux seemingly overnight after decades of Windows domination.
Copilot: a black box inflationary doodad riding the Nvidia wings after the crypto bubble; airplanes not falling from sky only because traffic control probably doesn't have it installed on critical hardware.

Finished “I’m Starting to Worry About This Black Box of Doom” by Jason Pargin. A Lyft driver is asked by a woman to drive her and a mysterious box across the country for $200k. The rules are that he cannot look inside, nor ask about the contents. Everything comes undone along the way in a mostly fun, pulpy thriller kind of way.
Some dark satire about anxiety, the web, social media, public discourse, incels, etc.
3.5/5 stars, rounded up to 4/5 ⭐️⭐️⭐️⭐️

Goodreads
Discover and share books you love on Goodreads.

If anyone needs me, I'll be in my box. :neocat_box:

#Anarchism #Syndicalism #AnarchoSyndicalism #Activism

from my link log —
Black-box concurrent data structures for NUMA architectures.
https://cs.brown.edu/~irina/papers/asplos2017-final.pdf
saved 2023-09-09

Limits to black-box amplification in QMA
Scott Aaronson, Freek Witteveen
https://arxiv.org/abs/2509.21131 https://arxiv.org/pdf/2509.21131

Limits to black-box amplification in QMA
We study the limitations of black-box amplification in the quantum complexity class QMA. Amplification is known to boost any inverse-polynomial gap between completeness and soundness to exponentially small error, and a recent result (Jeffery and Witteveen, 2025) shows that completeness can in fact be amplified to be doubly exponentially close to 1. We prove that this is optimal for black-box procedures: we provide a quantum oracle relative to which no QMA verification procedure using polynomial…

Rob Jetten of een debat waar ik geen zij ij heb.. Sja .... Dan maar naar de buren.
Polizeiruf 110: Black Box - hier anschauen
https://www.ardmediathek.de/video/polizeiruf-110/black-box/mdr/Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MDgwODEtMzg4NDk4

Black-box Context-free Grammar Inference for Readable & Natural Grammars
Mohammad Rifat Arefin, Shanto Rahman, Christoph Csallner
https://arxiv.org/abs/2509.26616 https://…

Black-box Context-free Grammar Inference for Readable & Natural Grammars
Black-box context-free grammar inference is crucial for program analysis, reverse engineering, and security, yet existing tools such as Arvada, TreeVada, and Kedavra struggle with scalability, readability, and accuracy on large, complex languages. We present NatGI, a novel LLM-guided grammar inference framework that extends TreeVada's parse tree recovery with three key innovations: bracket-guided bubble exploration, LLM- driven bubble generation and non-terminal labeling, and hierarchical delta…

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Stephen Ni-Hahn, Chao P\'eter Yang, Mingchen Ma, Cynthia Rudin, Simon Mak, Yue Jiang
https://arxiv.org/abs/2510.10249

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Artificial Intelligence (AI) for music generation is undergoing rapid developments, with recent symbolic models leveraging sophisticated deep learning and diffusion model algorithms. One drawback with existing models is that they lack structural cohesion, particularly on harmonic-melodic structure. Furthermore, such existing models are largely "black-box" in nature and are not musically interpretable. This paper addresses these limitations via a novel generative music framework that incorporate…

When did we move from a OKish "out of the box"-experience to a even worse "out of the black-box"-experience…

MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems
Shreeranjani Srirangamsridharan, Ali Abavisani, Reza Yousefi Maragheh, Ramin Giahi, Kai Zhao, Jason Cho, Sushant Kumar
https://arxiv.org/abs/2510.01523

MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems
Meta titles and descriptions strongly shape engagement in search and recommendation platforms, yet optimizing them remains challenging. Search engine ranking models are black box environments, explicit labels are unavailable, and feedback such as click-through rate (CTR) arrives only post-deployment. Existing template, LLM, and retrieval-augmented approaches either lack diversity, hallucinate attributes, or ignore whether candidate phrasing has historically succeeded in ranking. This leaves a g…

Probing Latent Knowledge Conflict for Faithful Retrieval-Augmented Generation
Linfeng Gao, Baolong Bi, Zheng Yuan, Le Wang, Zerui Chen, Zhimin Wei, Shenghua Liu, Qinggang Zhang, Jinsong Su
https://arxiv.org/abs/2510.12460

Probing Latent Knowledge Conflict for Faithful Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance the factuality of Large Language Models (LLMs). However, existing RAG systems often suffer from an unfaithfulness issue, where the model's response contradicts evidence from the retrieved context. Existing approaches to improving contextual faithfulness largely rely on external interventions, such as prompt engineering, decoding constraints, or reward-based fine-tuning. These works treat the LLM as a black box an…

🇺🇦 #NowPlaying on KEXP's #DriveTime
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

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
Yanjie Li, Yiming Cao, Dong Wang, Bin Xiao
https://arxiv.org/abs/2510.04257 https://…

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
Multimodal agents built on large vision-language models (LVLMs) are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection, especially through visual inputs. We introduce AgentTypo, a black-box red-teaming framework that mounts adaptive typographic prompt injection by embedding optimized text into webpage images. Our automatic typographic prompt injection (ATPI) algorithm maximizes prompt reconstruction by substituting captioners while minimizing human det…

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
Xiaochong Lan, Jie Feng, Yinxing Liu, Xinlei Shi, Yong Li
https://arxiv.org/abs/2510.08081

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
Ranking online reviews by their intrinsic quality is a critical task for e-commerce platforms and information services, impacting user experience and business outcomes. However, quality is a domain-dependent and dynamic concept, making its assessment a formidable challenge. Traditional methods relying on hand-crafted features are unscalable across domains and fail to adapt to evolving content patterns, while modern deep learning approaches often produce black-box models that lack interpretabili…

Machine Learning Powered Feasible Path Framework with Adaptive Sampling for Black-box Optimization
Zixuan Zhang, Xiaowei Song, Jiaming Li, Yujiao Zeng, Yaling Nie, Min Zhu, Dongyun Lu, Yibo Zhang, Xin Xiao, Jie Li
https://arxiv.org/abs/2509.21077

Machine Learning Powered Feasible Path Framework with Adaptive Sampling for Black-box Optimization
Black-box optimization (BBO) involves functions that are unknown, inexact and/or expensive-to-evaluate. Existing BBO algorithms face several challenges, including high computational cost from extensive evaluations, difficulty in handling complex constraints, lacking theoretical convergence guarantees and/or instability due to large solution quality variation. In this work, a machine learning-powered feasible path optimization framework (MLFP) is proposed for general BBO problems including compl…

Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
Patrick Wienholt, Sophie Caselitz, Robert Siepmann, Philipp Bruners, Keno Bressem, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
https://arxiv.org/abs/2510.09256

Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
To determine whether using discrete semantic entropy (DSE) to reject questions likely to generate hallucinations can improve the accuracy of black-box vision-language models (VLMs) in radiologic image based visual question answering (VQA). This retrospective study evaluated DSE using two publicly available, de-identified datasets: (i) the VQA-Med 2019 benchmark (500 images with clinical questions and short-text answers) and (ii) a diagnostic radiology dataset (206 cases: 60 computed tomography …

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

Boundary on the Table: Efficient Black-Box Decision-Based Attacks for Structured Data
Roie Kazoom, Yuval Ratzabi, Etamar Rothstein, Ofer Hadar
https://arxiv.org/abs/2509.22850 h…

Boundary on the Table: Efficient Black-Box Decision-Based Attacks for Structured Data
Adversarial robustness in structured data remains an underexplored frontier compared to vision and language domains. In this work, we introduce a novel black-box, decision-based adversarial attack tailored for tabular data. Our approach combines gradient-free direction estimation with an iterative boundary search, enabling efficient navigation of discrete and continuous feature spaces under minimal oracle access. Extensive experiments demonstrate that our method successfully compromises nearly …

free waves audio magma stressbox ig https://www.waves.com/black-friday-2025/free-plugin

Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
Jingqi Zhang, Ruibo Chen, Yingqing Yang, Peihua Mai, Heng Huang, Yan Pang
https://arxiv.org/abs/2510.02962

Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrighted material, raising the need for reliable safeguards against unauthorized use. Existing membership inference attacks (MIAs) and dataset-inference methods typically require access to internal signals such as logits, while current black-box approaches often rely on handcrafted prompts or a clean reference dataset for…

It's THAT time of year again - @lifting_the_lid_festival has opened up ticket sales for the fifth annual event this November!
Information, networking, entertainment, food for thought, discussions and all the best of deathly content is yours for a remarkably low price. A full three days of excitement awaits you - get your ticket here: htt…

Nick Drake - "The Making of Five Leaves Left" (2025)
My pre-order for this got canceled because there's a fucking moron in the White House, but I managed to snag another copy for twice the price. Would that that was the only negative impact of Drumpf.
#NowPlaying #NickDrake

Interactive semantic segmentation for phosphene vision neuroprosthetics https://arxiv.org/abs/2509.19957 "findings demonstrate the value of user feedback and the potential of gaze-guided semantic segmentation to enhance neuroprosthetic vision";

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[1/1]:
- Provably Scalable Black-Box Variational Inference with Structured Variational Families
Joohwan Ko, Kyurae Kim, Woo Chang Kim, Jacob R. Gardner

RAG-Pull: Imperceptible Attacks on RAG Systems for Code Generation
Vasilije Stambolic, Aritra Dhar, Lukas Cavigelli
https://arxiv.org/abs/2510.11195 https://

RAG-Pull: Imperceptible Attacks on RAG Systems for Code Generation
Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the need for model retraining. It does so by adding external data into the LLM's context. We develop a new class of black-box attack, RAG-Pull, that inserts hidden UTF characters into queries or external code repositories, redirecting retrieval toward malicious code, thereby breaking the models' safety alignment. We observe that query and code perturbat…

We don't allow cats on our dinner table, and they full well know that (their punishment when caught is corporal cuddling).
While I was out of the house just now and my wife asleep, the 13yo took this picture.
Oh yeah, my wife's laptop often seems to mysterious crash overnight..
#CatsOfMastodon

#Blakes7 Series A, Episode 05 - The Web
AVON: Neither can we.
BLAKE: I'll bear that in mind. [Tosses empty box away.]
AVON: Don't worry. I'll remind you.
[Novara and Geela approach. Blake and Avon rise. Avon draws his weapon.]
…

Reliability Sensitivity with Response Gradient
Siu-Kui Au, Zi-Jun Cao
https://arxiv.org/abs/2510.09315 https://arxiv.org/pdf/2510.09315

Reliability Sensitivity with Response Gradient
Engineering risk is concerned with the likelihood of failure and the scenarios when it occurs. The sensitivity of failure probability to change in system parameters is relevant to risk-informed decision making. Computing sensitivity is at least one level more difficult than the probability itself, which is already challenged by a large number of input random variables, rare events and implicit nonlinear `black-box' response. Finite difference with Monte Carlo probability estimates is spurious, …

An Integral Equation Method for Linear Two-Point Boundary Value Systems
Tianze Zhang, Yixuan Ma, Jun Wang
https://arxiv.org/abs/2510.06678 https://arxiv.or…

An Integral Equation Method for Linear Two-Point Boundary Value Systems
We present an integral equation-based method for the numerical solution of two-point boundary value systems. Special care is devoted to the mathematical formulation, namely the choice of the background Green's function that leads to a well-conditioned integral equation. We then make use of a high-order Nystrom discretization and a fast direct solver on the continuous level to obtain a black-box solver that is fast and accurate. A numerical study of the conditioning of different integral formula…

Manifolds and Modules: How Function Develops in a Neural Foundation Model
Johannes Bertram, Luciano Dyballa, T. Anderson Keller, Savik Kinger, Steven W. Zucker
https://arxiv.org/abs/2512.07869 https://arxiv.org/pdf/2512.07869 https://arxiv.org/html/2512.07869
arXiv:2512.07869v1 Announce Type: new
Abstract: Foundation models have shown remarkable success in fitting biological visual systems; however, their black-box nature inherently limits their utility for under- standing brain function. Here, we peek inside a SOTA foundation model of neural activity (Wang et al., 2025) as a physiologist might, characterizing each 'neuron' based on its temporal response properties to parametric stimuli. We analyze how different stimuli are represented in neural activity space by building decoding man- ifolds, and we analyze how different neurons are represented in stimulus-response space by building neural encoding manifolds. We find that the different processing stages of the model (i.e., the feedforward encoder, recurrent, and readout modules) each exhibit qualitatively different representational structures in these manifolds. The recurrent module shows a jump in capabilities over the encoder module by 'pushing apart' the representations of different temporal stimulus patterns; while the readout module achieves biological fidelity by using numerous specialized feature maps rather than biologically plausible mechanisms. Overall, we present this work as a study of the inner workings of a prominent neural foundation model, gaining insights into the biological relevance of its internals through the novel analysis of its neurons' joint temporal response patterns.
toXiv_bot_toot

#KI darf kein Black Box-Spielzeug für Großkonzerne bleiben – das fordert #Mistral AI und startet die Initiative „KI für Bürger“. Es geht um Transparenz, Teilhabe und die strategische Nutzung künstlicher Intelligenz zugunsten von Gesellschaft und Staat – statt „One Size fits all“-Lösungen aus der Cloud. W…

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
Ting Li, Yang Yang, Yipeng Yu, Liang Yao, Guoqing Chao, Ruifeng Xu
https://arxiv.org/abs/2510.11584

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to enhance attack performance. However, it is unable to generate human-readable explanations, and exhibits poor generalizability. In the past few years, large language models (LLMs) have demonstrated powerful capabilities in text comprehension, generation, and reas…

🌍 The climate crisis demands urgent action. But which actions are best?
Decision makers face tough trade-offs:
Policy A lowers emissions at home but increases reliance on imports.
Policy B cuts emissions long-term but raises unemployment short-term.
Policy C boosts jobs now but increases emissions in the near term.
None of these choices are simple. A policy that looks good locally may increase global emissions, or its effects may depend on what other countries d…

Developing a Cost-Effective Spectrometer: A Practical Approach
Mohammad Tahsin Alam, Zafrin Jahan Nikita, Yasir Mahmud, Rafichha Yeasmin, Fairuz Darimi Bushra, Sheikh Hasib Cheragee, Redwanul Talukder Zeem
https://arxiv.org/abs/2510.06703

Developing a Cost-Effective Spectrometer: A Practical Approach
The paper demonstrates the design and execution of a low-cost optical spectrometer that employs a webcam, diffraction grating & Python (a free, open-source programming language). The device's design prioritized economy and usability, with a black box casing to reduce stray light and increase measurement accuracy. A diffraction grating made from a DVD was used to split light into its constituent wavelengths, which were then collected by the camera. The calibration procedure used a RED TIDE USB65…

Semi-Analytic Solutions to the Noh Problem with a Black Box Equation of State
Seth Gerberding, Jeff Peterson, Jim Ferguson, Scott Ramsey
https://arxiv.org/abs/2509.16766 https:/…

Semi-Analytic Solutions to the Noh Problem with a Black Box Equation of State
The objective of this paper is to derive a method of constructing semi-analytic solutions to the Noh Problem when the equation of state (EoS) is a black box. Such solutions can be used for verification tests of hydrodynamics codes. We present the underlying theory, the method for finding solutions, and several examples of derived semi-analytic solutions. We end by performing a classic convergence test using a non-trivial semi-analytic solution.

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

On The Road - To Xi’An/ Departure II 🔜
在路上 - 去西安/ 离 II 🔜
📷 Pentax MX
🎞️Kodak Double-X 5222
#filmphotography #Photography #blackandwhite

In Praise of RSS and Controlled Feeds of Information
https://blog.burkert.me/posts/in_praise_of_syndication/

In Praise of RSS and Controlled Feeds of Information
The way we consume content on the internet is increasingly driven by walled-garden platforms and black-box feed algorithms. This shift is making our media diets miserable. Ironically, a solution to the problem predates algorithmic feeds, social media and other forms of informational junk food. It is called RSS (Really Simple Syndication) and it is beautiful. What the hell is RSS? RSS is just a format that defines how websites can publish updates (articles, posts, episodes, and so on) in a stand…

TCR-EML: Explainable Model Layers for TCR-pMHC Prediction
Jiarui Li, Zixiang Yin, Zhengming Ding, Samuel J. Landry, Ramgopal R. Mettu
https://arxiv.org/abs/2510.04377 https://…

TCR-EML: Explainable Model Layers for TCR-pMHC Prediction
T cell receptor (TCR) recognition of peptide-MHC (pMHC) complexes is a central component of adaptive immunity, with implications for vaccine design, cancer immunotherapy, and autoimmune disease. While recent advances in machine learning have improved prediction of TCR-pMHC binding, the most effective approaches are black-box transformer models that cannot provide a rationale for predictions. Post-hoc explanation methods can provide insight with respect to the input but do not explicitly model b…

ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test
Guan-Yan Yang, Tzu-Yu Cheng, Ya-Wen Teng, Farn Wanga, Kuo-Hui Yeh
https://arxiv.org/abs/2510.10281 htt…

ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test
The integration of Large Language Models (LLMs) into computer applications has introduced transformative capabilities but also significant security challenges. Existing safety alignments, which primarily focus on semantic interpretation, leave LLMs vulnerable to attacks that use non-standard data representations. This paper introduces ArtPerception, a novel black-box jailbreak framework that strategically leverages ASCII art to bypass the security measures of state-of-the-art (SOTA) LLMs. Unlik…

Clifford testing: algorithms and lower bounds
Marcel Hinsche, Zongbo Bao, Philippe van Dordrecht, Jens Eisert, Jop Bri\"et, Jonas Helsen
https://arxiv.org/abs/2510.07164 ht…

Clifford testing: algorithms and lower bounds
We consider the problem of Clifford testing, which asks whether a black-box $n$-qubit unitary is a Clifford unitary or at least $\varepsilon$-far from every Clifford unitary. We give the first 4-query Clifford tester, which decides this problem with probability $\mathrm{poly}(\varepsilon)$. This contrasts with the minimum of 6 copies required for the closely-related task of stabilizer testing. We show that our tester is tolerant, by adapting techniques from tolerant stabilizer testing to our se…

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
Aravindhan G, Yuvaraj Govindarajulu, Parin Shah
https://arxiv.org/abs/2509.22060

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on white-box attacks with constrained optimizations, and transferability based black-box attacks against commercial Automatic Speech Recognition devices, this paper explores cost efficient white-box attack and non transferability black-box adversarial attacks o…

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

I didn't choose fancy life, fancy life chose me.

Onto-Epistemological Analysis of AI Explanations
Martina Mattioli, Eike Petersen, Aasa Feragen, Marcello Pelillo, Siavash A. Bigdeli
https://arxiv.org/abs/2510.02996 https://

Onto-Epistemological Analysis of AI Explanations
Artificial intelligence (AI) is being applied in almost every field. At the same time, the currently dominant deep learning methods are fundamentally black-box systems that lack explanations for their inferences, significantly limiting their trustworthiness and adoption. Explainable AI (XAI) methods aim to overcome this challenge by providing explanations of the models' decision process. Such methods are often proposed and developed by engineers and scientists with a predominantly technical bac…

Effectiveness of Reconfigurable Intelligent Surface in Multipath Fading Channel
Hasnul Hashim
https://arxiv.org/abs/2510.00838 https://arxiv.org/pdf/2510.0…

Effectiveness of Reconfigurable Intelligent Surface in Multipath Fading Channel
A method of simulating a single-input single-output reconfigurable intelligent surface (RIS) assisted channel is presented using three channel black boxes to represent the direct signal path, the transmit path to the RIS and the reflected path from the RIS. The complex coefficients for each channel box is obtained by ray tracing in a scenario with geographic terrain information that also contains approximate building shapes. The electrical characteristics of the ground and building walls were a…

Replaced article(s) found for cs.CC. https://arxiv.org/list/cs.CC/new
[1/1]:
- Black-Box Crypto is Useless for Pseudorandom Codes
Sanjam Garg, Sam Gunn, Mingyuan Wang

Privately Estimating Black-Box Statistics
G\"unter F. Steinke, Thomas Steinke
https://arxiv.org/abs/2510.00322 https://arxiv.org/pdf/2510.00322…

Privately Estimating Black-Box Statistics
Standard techniques for differentially private estimation, such as Laplace or Gaussian noise addition, require guaranteed bounds on the sensitivity of the estimator in question. But such sensitivity bounds are often large or simply unknown. Thus we seek differentially private methods that can be applied to arbitrary black-box functions. A handful of such techniques exist, but all are either inefficient in their use of data or require evaluating the function on exponentially many inputs. In this…

NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information
Wei-Ting Tang, Akshay Kudva, Joel A. Paulson
https://arxiv.org/abs/2510.05516

NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information
Bayesian optimization (BO) is effective for expensive black-box problems but remains challenging in high dimensions. We propose NeST-BO, a local BO method that targets the Newton step by jointly learning gradient and Hessian information with Gaussian process surrogates, and selecting evaluations via a one-step lookahead bound on Newton-step error. We show that this bound (and hence the step error) contracts with batch size, so NeST-BO directly inherits inexact-Newton convergence: global progres…

Surrogate Graph Partitioning for Spatial Prediction
Yuta Shikuri, Hironori Fujisawa
https://arxiv.org/abs/2510.07832 https://arxiv.org/pdf/2510.07832

Surrogate Graph Partitioning for Spatial Prediction
Spatial prediction refers to the estimation of unobserved values from spatially distributed observations. Although recent advances have improved the capacity to model diverse observation types, adoption in practice remains limited in industries that demand interpretability. To mitigate this gap, surrogate models that explain black-box predictors provide a promising path toward interpretable decision making. In this study, we propose a graph partitioning problem to construct spatial segments tha…

Introduction to Interpolation-Based Optimization
Lindon Roberts
https://arxiv.org/abs/2510.04473 https://arxiv.org/pdf/2510.04473

Introduction to Interpolation-Based Optimization
The field of derivative-free optimization (DFO) studies algorithms for nonlinear optimization that do not rely on the availability of gradient or Hessian information. It is primarily designed for settings when functions are black-box, expensive to evaluate and/or noisy. A widely used and studied class of DFO methods for local optimization is interpolation-based optimization (IBO), also called model-based DFO, where the general principles from derivative-based nonlinear optimization algorithms a…

On The Road - To Xi’An/ Beings II 👁️‍🗨️
在路上 - 去西安/ 灵 II 👁️‍🗨️
📷 Pentax MX
🎞️Kodak Double-X 5222
#filmphotography #Photography #blackandwhite

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

Select your desktop environment... IF YOU DARE
#CatsOfMastodon

SADA: Safe and Adaptive Inference with Multiple Black-Box Predictions
Jiawei Shan, Yiming Dong, Jiwei Zhao
https://arxiv.org/abs/2509.21707 https://arxiv.o…

SADA: Safe and Adaptive Inference with Multiple Black-Box Predictions
Real-world applications often face scarce labeled data due to the high cost and time requirements of gold-standard experiments, whereas unlabeled data are typically abundant. With the growing adoption of machine learning techniques, it has become increasingly feasible to generate multiple predicted labels using a variety of models and algorithms, including deep learning, large language models, and generative AI. In this paper, we propose a novel approach that safely and adaptively aggregates mu…

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
Akchunya Chanchal, David A. Kelly, Hana Chockler
https://arxiv.org/abs/2510.01038 https://…

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
Black-box explainability methods are popular tools for explaining the decisions of image classifiers. A major drawback of these tools is their reliance on mutants obtained by occluding parts of the input, leading to out-of-distribution images. This raises doubts about the quality of the explanations. Moreover, choosing an appropriate occlusion value often requires domain knowledge. In this paper we introduce a novel forward-pass paradigm Activation-Deactivation (AD), which removes the effects o…

Walk the Talk: Is Your Log-based Software Reliability Maintenance System Really Reliable?
Minghua He, Tong Jia, Chiming Duan, Pei Xiao, Lingzhe Zhang, Kangjin Wang, Yifan Wu, Ying Li, Gang Huang
https://arxiv.org/abs/2509.24352

Walk the Talk: Is Your Log-based Software Reliability Maintenance System Really Reliable?
Log-based software reliability maintenance systems are crucial for sustaining stable customer experience. However, existing deep learning-based methods represent a black box for service providers, making it impossible for providers to understand how these methods detect anomalies, thereby hindering trust and deployment in real production environments. To address this issue, this paper defines a trustworthiness metric, diagnostic faithfulness, for models to gain service providers' trust, based o…

Eliciting Secret Knowledge from Language Models
Bartosz Cywi\'nski, Emil Ryd, Rowan Wang, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy, Samuel Marks
https://arxiv.org/abs/2510.01070

Eliciting Secret Knowledge from Language Models
We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to possess specific knowledge that they apply downstream but deny knowing when asked directly. For example, in one setting, we train an LLM to generate replies that are consistent with knowing the user is female, while denying this knowledge when asked directly. We then design various black-box and white-box secret elici…

Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
Xiangfang Li, Yu Wang, Bo Li
https://arxiv.org/abs/2510.01342 https://

Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks. However, most existing studies focus on overly simplified attack scenarios, limiting their practical relevance to real-world defense settings. To make this risk concrete, we present a three-pronged jailbreak attack and evaluate it against provider defenses under a…

ProfVLM: A Lightweight Video-Language Model for Multi-View Proficiency Estimation
Edoardo Bianchi, Jacopo Staiano, Antonio Liotta
https://arxiv.org/abs/2509.26278 https://

ProfVLM: A Lightweight Video-Language Model for Multi-View Proficiency Estimation
Existing approaches to skill proficiency estimation often rely on black-box video classifiers, ignoring multi-view context and lacking explainability. We present ProfVLM, a compact vision-language model that reformulates this task as generative reasoning: it jointly predicts skill level and generates expert-like feedback from egocentric and exocentric videos. Central to our method is an AttentiveGatedProjector that dynamically fuses multi-view features, projected from a frozen TimeSformer backb…

Series D, Episode 05 - Animals
VILA: Are we expecting trouble on this trip?
AVON: A federation patrol attacked Scorpio at Bucol Two. They might wonder what it was doing there in the first place. I would in their position.
https://blake.torpidity.net/m/405/287 B7B4

Filling up your timeline

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
Akchunya Chanchal, David A. Kelly, Hana Chockler
https://arxiv.org/abs/2510.01038 https://…

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
Black-box explainability methods are popular tools for explaining the decisions of image classifiers. A major drawback of these tools is their reliance on mutants obtained by occluding parts of the input, leading to out-of-distribution images. This raises doubts about the quality of the explanations. Moreover, choosing an appropriate occlusion value often requires domain knowledge. In this paper we introduce a novel forward-pass paradigm Activation-Deactivation (AD), which removes the effects o…

Quantile-Scaled Bayesian Optimization Using Rank-Only Feedback
Tunde Fahd Egunjobi
https://arxiv.org/abs/2510.03277 https://arxiv.org/pdf/2510.03277…

Quantile-Scaled Bayesian Optimization Using Rank-Only Feedback
Bayesian Optimization (BO) is widely used for optimizing expensive black-box functions, particularly in hyperparameter tuning. However, standard BO assumes access to precise objective values, which may be unavailable, noisy, or unreliable in real-world settings where only relative or rank-based feedback can be obtained. In this study, we propose Quantile-Scaled Bayesian Optimization (QS-BO), a principled rank-based optimization framework. QS-BO converts ranks into heteroscedastic Gaussian targe…

GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning
Silvia Sapora, Devon Hjelm, Alexander Toshev, Omar Attia, Bogdan Mazoure
https://arxiv.org/abs/2510.02180

GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning
Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield "black-box" models that are difficult to interpret and debug. In this work, we introduce GRACE (Generating Rewards As CodE), a method for using Large Language Models within an evolutionary search to reverse-engineer an interpretable, code-based reward function directly from expert trajectories. The resulting reward function is executable code that can be inspected and verified.…

Modular and Adaptive Conformal Prediction for Sequential Models via Residual Decomposition
William Zhang, Saurabh Amin, Georgia Perakis
https://arxiv.org/abs/2510.04406 https://…

Modular and Adaptive Conformal Prediction for Sequential Models via Residual Decomposition
Conformal prediction offers finite-sample coverage guarantees under minimal assumptions. However, existing methods treat the entire modeling process as a black box, overlooking opportunities to exploit modular structure. We introduce a conformal prediction framework for two-stage sequential models, where an upstream predictor generates intermediate representations for a downstream model. By decomposing the overall prediction residual into stage-specific components, our method enables practition…

Knock-Knock: Black-Box, Platform-Agnostic DRAM Address-Mapping Reverse Engineering
Antoine Plin, Lorenzo Casalino, Thomas Rokicki, Ruben Salvador
https://arxiv.org/abs/2509.19568

Knock-Knock: Black-Box, Platform-Agnostic DRAM Address-Mapping Reverse Engineering
Modern Systems-on-Chip (SoCs) employ undocumented linear address-scrambling functions to obfuscate DRAM addressing, which complicates DRAM-aware performance optimizations and hinders proactive security analysis of DRAM-based attacks; most notably, Rowhammer. Although previous work tackled the issue of reversing physical-to-DRAM mapping, existing heuristic-based reverse-engineering approaches are partial, costly, and impractical for comprehensive recovery. This paper establishes a rigorous theor…

Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation
Ruoyu Chen, Xiaoqing Guo, Kangwei Liu, Siyuan Liang, Shiming Liu, Qunli Zhang, Hua Zhang, Xiaochun Cao
https://arxiv.org/abs/2509.22496

Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated tokens depend on visual modalities remains poorly understood, limiting interpretability and reliability. In this work, we present EAGLE, a lightweight black-box framework for explaining autoregressive token generation in MLLMs. EAGLE attributes any selected tokens to compact perceptual regions while quantifying the relativ…

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

LLM Agents for Knowledge Discovery in Atomic Layer Processing
Andreas Werbrouck, Marshall B. Lindsay, Matthew Maschmann, Matthias J. Young
https://arxiv.org/abs/2509.26201 https…

LLM Agents for Knowledge Discovery in Atomic Layer Processing
Large Language Models (LLMs) have garnered significant attention for several years now. Recently, their use as independently reasoning agents has been proposed. In this work, we test the potential of such agents for knowledge discovery in materials science. We repurpose LangGraph's tool functionality to supply agents with a black box function to interrogate. In contrast to process optimization or performing specific, user-defined tasks, knowledge discovery consists of freely exploring the syste…

Circuit Distillation
Somin Wadhwa, Silvio Amir, Byron C. Wallace
https://arxiv.org/abs/2509.25002 https://arxiv.org/pdf/2509.25002

Circuit Distillation
Model distillation typically focuses on behavioral mimicry, where a student model is trained to replicate a teacher's output while treating its internal computations as a black box. In this work we propose an alternative approach: Distilling the underlying computational mechanisms implemented by a teacher model. Specifically, we propose circuit distillation, which introduces an objective to align internal representations between analogous circuit components in teacher and student models. We pro…

Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applications
Maraz Mia, Mir Mehedi A. Pritom
https://arxiv.org/abs/2510.03623 https://…

Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applications
Explainable Artificial Intelligence (XAI) has aided machine learning (ML) researchers with the power of scrutinizing the decisions of the black-box models. XAI methods enable looking deep inside the models' behavior, eventually generating explanations along with a perceived trust and transparency. However, depending on any specific XAI method, the level of trust can vary. It is evident that XAI methods can themselves be a victim of post-adversarial attacks that manipulate the expected outcome f…

Learning Conformal Explainers for Image Classifiers
Amr Alkhatib, Stephanie Lowry
https://arxiv.org/abs/2509.21209 https://arxiv.org/pdf/2509.21209

Learning Conformal Explainers for Image Classifiers
Feature attribution methods are widely used for explaining image-based predictions, as they provide feature-level insights that can be intuitively visualized. However, such explanations often vary in their robustness and may fail to faithfully reflect the reasoning of the underlying black-box model. To address these limitations, we propose a novel conformal prediction-based approach that enables users to directly control the fidelity of the generated explanations. The method identifies a subset…

LAVA: Explainability for Unsupervised Latent Embeddings
Ivan Stresec, Joana P. Gon\c{c}alves
https://arxiv.org/abs/2509.21149 https://arxiv.org/pdf/2509.21…

LAVA: Explainability for Unsupervised Latent Embeddings
Unsupervised black-box models can be drivers of scientific discovery, but remain difficult to interpret. Crucially, discovery hinges on understanding the model output, which is often a multi-dimensional latent embedding rather than a well-defined target. While explainability for supervised learning usually seeks to uncover how input features are used to predict a target, its unsupervised counterpart should relate input features to the structure of the learned latent space. Adaptations of superv…

Privacy in the Age of AI: A Taxonomy of Data Risks
Grace Billiris, Asif Gill, Madhushi Bandara
https://arxiv.org/abs/2510.02357 https://arxiv.org/pdf/2510.…

Privacy in the Age of AI: A Taxonomy of Data Risks
Artificial Intelligence (AI) systems introduce unprecedented privacy challenges as they process increasingly sensitive data. Traditional privacy frameworks prove inadequate for AI technologies due to unique characteristics such as autonomous learning and black-box decision-making. This paper presents a taxonomy classifying AI privacy risks, synthesised from 45 studies identified through systematic review. We identify 19 key risks grouped under four categories: Dataset-Level, Model-Level, Infras…

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty
Lingyou Pang, Lei Huang, Jianyu Lin, Tianyu Wang, Akira Horiguchi, Alexander Aue, Carey E. Priebe
https://arxiv.org/abs/2509.23002

Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty
Deploying black-box LLMs requires managing uncertainty in the absence of token-level probability or true labels. We propose introducing an unsupervised conformal inference framework for generation, which integrates: generative models, incorporating: (i) an LLM-compatible atypical score derived from response-embedding Gram matrix, (ii) UCP combined with a bootstrapping variant (BB-UCP) that aggregates residuals to refine quantile precision while maintaining distribution-free, finite-sample cover…

Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning
Sanish Suwal, Shaurya Garg, Dipkamal Bhusal, Michael Clifford, Nidhi Rastogi
https://arxiv.org/abs/2509.20148

Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning
Connected and autonomous vehicles continue to heavily rely on AI systems, where transparency and security are critical for trust and operational safety. Post-hoc explanations provide transparency to these black-box like AI models but the quality and reliability of these explanations is often questioned due to inconsistencies and lack of faithfulness in representing model decisions. This paper systematically examines the impact of three widely used training approaches, namely natural training, a…

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

Symmetry-Aware Bayesian Optimization via Max Kernels
Anthony Bardou, Antoine Gonon, Aryan Ahadinia, Patrick Thiran
https://arxiv.org/abs/2509.25051 https://

Symmetry-Aware Bayesian Optimization via Max Kernels
Bayesian Optimization (BO) is a powerful framework for optimizing noisy, expensive-to-evaluate black-box functions. When the objective exhibits invariances under a group action, exploiting these symmetries can substantially improve BO efficiency. While using maximum similarity across group orbits has long been considered in other domains, the fact that the max kernel is not positive semidefinite (PSD) has prevented its use in BO. In this work, we revisit this idea by considering a PSD projectio…

🇺🇦 Auf radioeins läuft...
Automatic:
🎵 Black Box
#NowPlaying #Automatic
https://blackflooddixon.bandcamp.com/track/peppermint-box
https://open.spotify.com/track/45c2puZgmaC23MaKgeHda2

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
Miao Yu, Zhenhong Zhou, Moayad Aloqaily, Kun Wang, Biwei Huang, Stephen Wang, Yueming Jin, Qingsong Wen
https://arxiv.org/abs/2509.21761

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus on alignment, jailbreak, and hallucination, but overlooks backdoor mechanisms, making it difficult to understand and fully eliminate the backdoor threat. In this paper, aiming to bridge this gap, we explore the interpretable mechanisms of LLM backdoors through…