Skip to content

Scan record

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

Nov 1839 loaded

  1. FT asks: Is AI financial advice credible?

    NewsFinancial Times · AIOpinionThe item you came from

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

    NewsWIRED Security and AIAI updates

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

    NewsMinistry of HealthGovernance

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

    PaperarXiv: AI Governance & Policy

  5. 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

  6. ARC-2: Continuous Compliance via Delta Management

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  9. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  17. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  21. 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

  22. Visual backdoors grow as student model rollouts continue

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  29. EGS: a supplementary safety framework for educational LLMs

    PaperarXiv: 其他 AI 安全论文

  30. 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

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

    PaperarXiv: 其他 AI 安全论文

  32. MedGuardBench: A Benchmark for Developing Patient-Facing Personalized Guardrails

    PaperarXiv: 其他 AI 安全论文

  33. WebAgents: splitting agent creation, hosting, and execution for the agent-native Web

    PaperarXiv: 其他 AI 安全论文

  34. Wrong Inputs, Wrong Thresholds: Re-evaluating Adversarial Face Privacy

    PaperarXiv: 其他 AI 安全论文

  35. Auditors struggle to detect deliberate sabotage from end-to-end records of AI safety research

    PaperarXiv: 其他 AI 安全论文

  36. The Threat Landscape of Vibe Coding and the Path to Safe Autonomy

    PaperarXiv: 其他 AI 安全论文

  37. Chain-of-thought controllability reduces chain-of-thought monitorability

    PaperarXiv: 其他 AI 安全论文

  38. Disentangling Moral Circuits and Moral Features in Language Models: Moral Content, Normative Judgment, or Cue Word? Evidence from 14 Models

    PaperarXiv: 其他 AI 安全论文

  39. Depth-Aware Activation Steering Based on Attention Residuals

    PaperarXiv: 其他 AI 安全论文