arXiv AI
Jul 23
The Ethics of Autonomous AI Agents for Offensive Security
arXiv:2607. 20255v1 Announce Type: cross Abstract: LLM-driven autonomous agents are reshaping offensive security.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv Machine Learning
Jul 23
SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding
arXiv:2503. 06437v3 Announce Type: replace-cross Abstract: We present SEED (Semantic Evaluation for Visual Brain Decoding), a novel metric for evaluating the semantic decoding performance of visual brain decoding models.
arXiv AI
Jul 23
StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation
arXiv:2607. 20174v1 Announce Type: cross Abstract: Existing human--object interaction (HOI) video generation methods are largely limited to offline short-video generation with complex driving conditions, making them unsuitable for real-time interactive applications.
arXiv AI
Jul 23
Information Discernment in Large Language Models
arXiv:2607. 19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet.
arXiv AI
Jul 23
Pre-Deployment Complexity Estimation for Federated Perception Systems
arXiv:2603. 28282v2 Announce Type: replace-cross Abstract: Edge AI systems increasingly rely on federated learning to train perception models in distributed, privacy-preserving, and resource-constrained environments.
arXiv AI
Jul 23
Cross-Subject Semantic Decoding with Shared-Space Alignment for Generalized Neural Representation Learning
arXiv:2607. 19394v1 Announce Type: cross Abstract: Generalizing across subjects remains challenging in invasive neural recordings because electrode configurations, anatomical structures, and neural signal patterns vary substantially across individuals.
arXiv AI
Jul 23
Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics
arXiv:2607. 19389v1 Announce Type: cross Abstract: As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn attention.
arXiv Machine Learning
Jul 23
Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment
arXiv:2607. 20073v1 Announce Type: new Abstract: AI-based recruitment systems that rely on machine learning models trained on historical CV data, risk perpetuating and amplifying social biases.
arXiv AI
Jul 23
GraphContainer: A Unified Platform for Comparing and Debugging Graph RAG Methods
arXiv:2607. 19362v1 Announce Type: new Abstract: Graph RAG mitigates hallucinations and stale knowledge in LLMs, particularly for multi-hop question answering.
arXiv Machine Learning
Jul 23
Data-Poisoning Audits for Causal Effect Estimation
arXiv:2607. 19692v1 Announce Type: cross Abstract: Observational causal analyses increasingly pool records across sites, vendors, and collection systems, creating vulnerability to append-only attacks in which plausible records are strategically selected to alter a reported treatment effect.
arXiv AI
Jul 23
FSDBN: Foreground-Aware EEG-Visual Alignment via Dynamic Brain Networks
arXiv:2607. 18344v2 Announce Type: replace-cross Abstract: EEG-based visual decoding provides a non-invasive pathway for interpreting visual semantics.
arXiv AI
Jul 23
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
arXiv:2607. 19913v1 Announce Type: new Abstract: Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act.
arXiv AI
Jul 23
PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
arXiv:2607. 20268v1 Announce Type: new Abstract: While Large Language Models (LLMs) excel at many tasks, they frequently struggle with complex reasoning that requires long-horizon planning and iterative error correction.
arXiv Machine Learning
Jul 23
Online Variance Reduction for Domain Adaptation on Streaming Data
arXiv:2607. 20374v1 Announce Type: new Abstract: This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions.
arXiv AI
Jul 23
SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data
arXiv:2607. 19949v1 Announce Type: new Abstract: Smartphone personal assistants reason over longitudinal personal data, yet evaluating them requires context-rich evaluation data whose correct answers are known, and real device traces are too privacy-sensitive to share.
arXiv AI
Jul 23
CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs
arXiv:2607. 19396v1 Announce Type: new Abstract: Document-based LLM systems often flatten a PDF before guardrails inspect it.
arXiv AI
Jul 23
Causal dictionary learning reveals and validates transcription-factor binding features in genomic language models
arXiv:2607. 19618v1 Announce Type: cross Abstract: Genomic language models achieve strong performance across regulatory-genomics tasks, yet what these models internally represent remains opaque, and the field lacks a principled procedure for verifying that an apparent ``concept'' inside a model is real rather than an artifact of sequence composition.
arXiv AI
Jul 23
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
arXiv:2601. 06487v3 Announce Type: replace-cross Abstract: Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.
arXiv Machine Learning
Jul 23
Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis
arXiv:2602. 16144v4 Announce Type: replace-cross Abstract: As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy.
arXiv Machine Learning
Jul 23
Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation
arXiv:2607. 19855v1 Announce Type: new Abstract: Adversarial robustness is commonly evaluated with predefined attack ensembles, such as AutoAttack, at a single perturbation budget $\varepsilon$ and on a selective choice of perturbation norms.