Skip to content

Scan record

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

Yesterday · Nov 1940 loaded

  1. CCN updates ENS information security policy and responsibilities and functions guidance, adding an appendix linking data protection and AI rules

    NewsCentro Criptológico NacionalGovernanceThe item you came from

  2. Can you make a model believe false facts in the prompt?

    PaperarXiv: Alignment, Deception & Oversight

  3. Dependency fabrication in repository deployment agents

    PaperarXiv: Alignment, Deception & Oversight

  4. Nudge Security report: AI agents inherit employee access permissions, and their use is unsupervised

    NewsHelp Net Security AIEvent

  5. Negotiating control and accountability among stakeholders in high-risk AI application scenarios: development and evaluation of the ALIGN method

    PaperarXiv: 其他 AI 安全论文

  6. RECLAIM: robot vision-guided adversarial patch defense via embodied attention feedback

    PaperarXiv: 其他 AI 安全论文

  7. Truthgate: Checking coding agents' behavior against records they cannot edit—cheating, deterrence and disclosure on impossible tasks

    PaperarXiv: 其他 AI 安全论文

  8. PGPO: prototype-guided progressive obfuscation for privacy-preserving LLM-enhanced recommendation

    PaperarXiv: 其他 AI 安全论文

  9. Kaer: safety-aware replanning for multi-agent systems

    PaperarXiv: 其他 AI 安全论文

  10. Exactly stealing other clients' training data in federated learning

    PaperarXiv: 其他 AI 安全论文

  11. The limitation is in the input, not the model: state-dependent command safety in natural language interfaces for industrial controllers

    PaperarXiv: 其他 AI 安全论文

  12. Gradient-based defensive poisoning against system identification attacks on cyber-physical systems

    PaperarXiv: 其他 AI 安全论文

  13. GateWatch: Low-overhead LLM monitoring with Boolean circuits

    PaperarXiv: 其他 AI 安全论文

  14. SCR: Detecting Backdoor-Poisoned Samples via Clean Reference Residuals

    PaperarXiv: 其他 AI 安全论文

  15. Probing agent over-proactiveness in real-world settings with Continuation Audits

    PaperarXiv: 其他 AI 安全论文

  16. Nothing to Declare: Steering a Single Neuron Increases Concealment in Agent Teams

    PaperarXiv: 其他 AI 安全论文

  17. PIPETTE: prompt injection purple teaming for robust LLM agents

    PaperarXiv: 其他 AI 安全论文

  18. Can Weight-Space Programming Change a Model's Learned Ethical Priorities?

    PaperarXiv: 其他 AI 安全论文

  19. AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents

    PaperarXiv: 其他 AI 安全论文

  20. When shuffling fails: recovering tokens from obfuscated KV caches

    PaperarXiv: 其他 AI 安全论文

  21. What survives in the shift from text to pixels? Conditional protection against prompt injection in documents rendered as images

    PaperarXiv: 其他 AI 安全论文

  22. Learning to Coordinate: LLM-Guided Workflow Evolution for Token-Efficient Red Teaming

    PaperarXiv: 其他 AI 安全论文

  23. Guarding the kingdom of skilled agents in a computational AI dynasty: control-flow integrity for agent skills

    PaperarXiv: 其他 AI 安全论文

  24. VESPA: Verifiable Symbolic Policy Adaptation for Safe Reinforcement Learning

    PaperarXiv: 其他 AI 安全论文

  25. Intent contracts: taking tools out of the agent's hands

    PaperarXiv: 其他 AI 安全论文

  26. SCAFFOLD: Toward Credential-Preserving Evidence Transfer for Reusable LLM Agent Skills

    PaperarXiv: 其他 AI 安全论文

  27. When can decision models help LLM-driven network discovery?

    PaperarXiv: 其他 AI 安全论文

  28. Rank-one bypass of fixed linear erasure

    PaperarXiv: 其他 AI 安全论文

  29. Weighing the Envelope: Component Weights and Arbitration in Single-LLM-Agent Envelope-Layer Defenses

    PaperarXiv: 其他 AI 安全论文

  30. DetectViT: Test-Time Backdoor Detection for Vision Transformers Based on Inter-Head Attention Discrepancies

    PaperarXiv: 其他 AI 安全论文

  31. Data poisoning attacks against local differential privacy triangle counting protocols

    PaperarXiv: 其他 AI 安全论文

  32. Safe Personal RSI: Evaluating and repairing personal agent updates

    PaperarXiv: 其他 AI 安全论文

  33. ACaM: automated capability modeling for agent security

    PaperarXiv: 其他 AI 安全论文

  34. Training Language Models for Introspective Oversight

    PaperarXiv: 其他 AI 安全论文

  35. TRACE-MAS: Diagnosing and repairing collaboration failures in multi-agent systems

    PaperarXiv: 其他 AI 安全论文

  36. Safety defenses and auditing for long-horizon LLM agents: State transition auditing and control in the agent harness

    PaperarXiv: 其他 AI 安全论文

  37. The mutually beneficial relationship between humans and AI is unstable under capability asymmetry

    PaperarXiv: 其他 AI 安全论文

  38. YUL: Bringing software supply chain security to coding agents

    PaperarXiv: 其他 AI 安全论文

  39. Examining retry transparency in agent tools

    PaperarXiv: 其他 AI 安全论文

  40. Who changed the AI agent's rules? Measuring how AI coding agents expand permissions in CI/CD pipelines

    PaperarXiv: 其他 AI 安全论文