Skip to content

Scan record

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

Yesterday · Nov 1940 loaded

  1. 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The item you came from

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

    PaperarXiv: 其他 AI 安全论文

  3. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  7. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  17. 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

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

    PaperarXiv: 其他 AI 安全论文

  19. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  24. Rank-one bypass of fixed linear erasure

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  29. ACaM: automated capability modeling for agent security

    PaperarXiv: 其他 AI 安全论文

  30. Training Language Models for Introspective Oversight

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  32. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  35. Examining retry transparency in agent tools

    PaperarXiv: 其他 AI 安全论文

  36. 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

  37. Agent-native applications: a new application paradigm

    PaperarXiv: 其他 AI 安全论文

  38. Tencent AI-Infra-Guard v4.6.11 released: adds the CoTInjection prompt security operator

    NewsTencent AI-Infra-Guard ReleasesTools

  39. Sam Altman says OpenAI will not advance unsupervised recursive self-improvement for now, and has invited four organizations on site for safety evaluation

    NewsWeChat · AI Era (Xinzhiyuan)Governance

  40. Anthropic lists on Nasdaq tonight: raising 81.3 billion USD, with nearly 90 scholars signing an open letter in opposition

    NewsWeChat · AI Era (Xinzhiyuan)AI updates