Tootfinder

Adversarial Text Generation with Dynamic Contextual Perturbation
Hetvi Waghela, Jaydip Sen, Sneha Rakshit, Subhasis Dasgupta
https://arxiv.org/abs/2506.09148

Adversarial Text Generation with Dynamic Contextual Perturbation
Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically focus on word-level or local text segment alterations, overlooking the broader context, which results in detectable or semantically inconsistent perturbations. We propose a novel adversarial text attack scheme named Dynamic Contextual Perturbation (DCP). DCP dyn…

»Spionage möglich – 40.000 Sicherheitskameras hängen ungeschützt am Netz:
Forscher haben Tausende von Sicherheitskameras entdeckt, auf die mit einem Webbrowser frei zugegriffen werden kann. Nicht mal Passwörter werden abgefragt.«
Dies ist "seriöse" Einschüchterung der Menschen und doch sind einige Kameras nur Attrappen die "Panne" haben. Die, die funzen, sind u.a. auch über das Web per @…

Spionage möglich: 40.000 Sicherheitskameras hängen ungeschützt am Netz - Golem.de
Forscher haben Tausende von Sicherheitskameras entdeckt, auf die mit einem Webbrowser frei zugegriffen werden kann. Nicht mal Passwörter werden abgefragt.

Optimal Non-Adaptive Group Testing with One-Sided Error Guarantees
Daniel McMorrow, Jonathan Scarlett
https://arxiv.org/abs/2506.10374 https://

Optimal Non-Adaptive Group Testing with One-Sided Error Guarantees
The group testing problem consists of determining a sparse subset of defective items from within a larger set of items via a series of tests, where each test outcome indicates whether at least one defective item is included in the test. We study the approximate recovery setting, where the recovery criterion of the defective set is relaxed to allow a small number of items to be misclassified. In particular, we consider one-sided approximate recovery criteria, where we allow either only false neg…

"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
Kellie Yu Hui Sim, Roy Ka-Wei Lee, Kenny Tsu Wei Choo
https://arxiv.org/abs/2506.09354

"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
Mental health is a growing global concern, prompting interest in AI-driven solutions to expand access to psychosocial support. Peer support, grounded in lived experience, offers a valuable complement to professional care. However, variability in training, effectiveness, and definitions raises concerns about quality, consistency, and safety. Large Language Models (LLMs) present new opportunities to enhance peer support interactions, particularly in real-time, text-based interactions. We present …

#Jellyfin for #Roku 3.0.5 will be published on Tuesday, Jun 10, 2025 5:00 PM PT
🎉 New Features
* Add ability to play album starting from selected track on album screen using play button by michaelcresswell
* Add ability to play playlist starting from selected track on playlist sc…

Large language models can learn and generalize steganographic chain-of-thought under process supervision
Joey Skaf, Luis Ibanez-Lissen, Robert McCarthy, Connor Watts, Vasil Georgiv, Hannes Whittingham, Lorena Gonzalez-Manzano, David Lindner, Cameron Tice, Edward James Young, Puria Radmard
https://arxiv.org/abs/2506.01926

Large language models can learn and generalize steganographic chain-of-thought under process supervision
Chain-of-thought (CoT) reasoning not only enhances large language model performance but also provides critical insights into decision-making processes, marking it as a useful tool for monitoring model intent and planning. By proactively preventing models from acting on CoT indicating misaligned or harmful intent, CoT monitoring can be used to reduce risks associated with deploying models. However, developers may be incentivized to train away the appearance of harmful intent from CoT traces, by …

This https://arxiv.org/abs/2506.00891 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Uneven Event Modeling for Partially Relevant Video Retrieval
Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments, wherein event modeling is crucial for partitioning the video into smaller temporal events that partially correspond to the text. Previous methods typically segment videos into a fixed number of equal-length clips, resulting in ambiguous event boundaries. Additionally, they rely on mean pooling to compute event representations, inevitably introducing undesired misalignment…

This https://arxiv.org/abs/2503.02077 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMA_…

M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality ($\text{M}^3\text{HF}$), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterat…

This https://arxiv.org/abs/2506.00261 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

GPR: Empowering Generation with Graph-Pretrained Retriever
Graph retrieval-augmented generation (GRAG) places high demands on graph-specific retrievers. However, existing retrievers often rely on language models pretrained on plain text, limiting their effectiveness due to domain misalignment and structure ignorance. To address these challenges, we propose GPR, a graph-based retriever pretrained directly on knowledge graphs. GPR aligns natural language questions with relevant subgraphs through LLM-guided graph augmentation and employs a structure-aware…

This https://arxiv.org/abs/2403.11981 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
We present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the training data to induce a targeted misclassification of a test-time input. Inspired by the adversarial robustness achieved by $randomized$ $smoothing$, we show how an off-the-shelf diffusion denoising model can sanitize the tampered training data. We extensively test our defense…