Skip to content

Scan record

Everything the site collected, newest first by collection time (Beijing time), back seven days.

Nov 1840 loaded

  1. Large-scale neuron community discovery reveals sparse neuron behavior in LLMs

    PaperarXivThe item you came from

  2. Colombo: a frontier-to-frontier automated research system for oracle-based optimization

    PaperarXiv

  3. Validating agents in rubric-based environments

    PaperarXiv

  4. SkillBuffBench: measuring the contribution of Agent Skills across harnesses, models, skill access modes and memory

    PaperarXiv

  5. Colombia-Meta cooperation plan covers responsible AI and anti-fraud

    NewsMINTIC ColombiaAI updates

  6. Offsec Harness Index: an evidence index of AI penetration tools actually abused by attackers

    Newsoffsecharnesses.aiEvent

  7. From TeleChat to Xing4: Advancing Frontier Agent Models on Domestic Chips and Frameworks

    PaperHugging Face Daily Papers

  8. Author says persuasiveness in AI evaluations exceeds humans, with no evidence for real-world political persuasion

    NewsLessWrongOpinion

  9. Paris Hilton returns to the U.S. Congress to push for a House vote on a deepfake pornography bill

    NewsCBS News · TechnologyGovernance

  10. FT asks: Is AI financial advice credible?

    NewsFinancial Times · AIOpinion

  11. Gallup survey: More than one-third of Gen Z in 16 countries use AI for companionship

    NewsWIRED Security and AIAI updates

  12. Singapore Ministry of Health discusses healthcare AI oversight and community trials

    NewsMinistry of HealthGovernance

  13. Honest brokers in AI regulation: how public comments introduce evidence to regulators

    PaperarXiv: AI Governance & Policy

  14. GuardAgent: A Memory-Augmented Agent Framework for Adaptive Detection of Adversarial Promotion in LLM-Based Recommender Systems

    PaperarXiv: 其他 AI 安全论文

  15. ARC-2: Continuous Compliance via Delta Management

    PaperarXiv: 其他 AI 安全论文

  16. Ethical Suppression in AI Development: A Comparative Case Study of Responsible AI under Competitive Pressure

    PaperarXiv: 其他 AI 安全论文

  17. Reading Scene States: Revealing Safety Failures of Vision-Language Models

    PaperarXiv: 其他 AI 安全论文

  18. Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organizational Autonomous Agents

    PaperarXiv: 其他 AI 安全论文

  19. Hidden-state similarity predicts the re-elicitation of suppressed behavior after inoculation prompting

    PaperarXiv: 其他 AI 安全论文

  20. SEAM: Computer-Use Agents Know the Harm Between Screens but Do It Anyway

    PaperarXiv: 其他 AI 安全论文

  21. Who Pays for Byzantine Robustness? Effectiveness, Data-Share Dictatorship, and Fairness under Few-Hospital Collaboration

    PaperarXiv: 其他 AI 安全论文

  22. Stopping Is Not the Limit: Understanding and Eliciting Agent Capabilities in Long-Horizon Vulnerability Exploitation

    PaperarXiv: 其他 AI 安全论文

  23. Against Coercion: AI Alignment as a Synthetic Social Contract

    PaperarXiv: 其他 AI 安全论文

  24. Network Exposure Configuration Attacks Against LLM-Controlled Social Robots

    PaperarXiv: 其他 AI 安全论文

  25. RefCloth: A Transferable Adversarial Tablecloth for Vision-Language-Action Models

    PaperarXiv: 其他 AI 安全论文

  26. Correct diagnosis, unsafe path: auditing clinical AI decision trajectories and the effectiveness and potential harms of corrective oversight

    PaperarXiv: 其他 AI 安全论文

  27. Propose with Gradients, Accept with Loss: A Hedged Attack for Pixel-Sparse Robustness

    PaperarXiv: 其他 AI 安全论文

  28. Adaptive LLM-Driven Honeypots Against LLM-Driven Attackers: Can Narrative Coherence Improve Deception Effectiveness?

    PaperarXiv: 其他 AI 安全论文

  29. Evolution Under Fire: Evolving Agent Safety Guardrails with Adaptive Injection Pressure

    PaperarXiv: 其他 AI 安全论文

  30. Letting Disagreement Surface Beats Resolving It: A Gated Ablation Study of Provenance-Weighted Memory in Multi-Agent Debate

    PaperarXiv: 其他 AI 安全论文

  31. Visual backdoors grow as student model rollouts continue

    PaperarXiv: 其他 AI 安全论文

  32. Bad Apples in the Kitchen: How LLM Teams Detect, Correct, and Calibrate Against Misaligned Members

    PaperarXiv: 其他 AI 安全论文

  33. Cloaked in authority: a practical black-box jailbreak of MLLMs exploiting visual trust bias

    PaperarXiv: 其他 AI 安全论文

  34. ConfGuard: A Physics-Grounded Reference Monitor for Predictive Maintenance LLM Agents

    PaperarXiv: 其他 AI 安全论文

  35. DACE: Diversity-Driven Adversarial Co-Evolution for Robust LLM Safety Alignment

    PaperarXiv: 其他 AI 安全论文

  36. From token changes to task failure: bit flips in shared KV cache blocks

    PaperarXiv: 其他 AI 安全论文

  37. GapLeak: when privacy-protecting LLM web agents become a privacy risk

    PaperarXiv: 其他 AI 安全论文

  38. EGS: a supplementary safety framework for educational LLMs

    PaperarXiv: 其他 AI 安全论文

  39. Is 4-bit Quantization More Than Noise for Chat Model Safety Behavior? Attributing Behavior Change with Matched Perturbations

    PaperarXiv: 其他 AI 安全论文

  40. Can You Undo That? Reversibility Grading of AI Agent Operations

    PaperarXiv: 其他 AI 安全论文