Skip to content

Scan record

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

Yesterday · Nov 1940 loaded

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

    PaperarXiv: 其他 AI 安全论文The item you came from

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  4. 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

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

    PaperarXiv: 其他 AI 安全论文

  6. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  11. Rank-one bypass of fixed linear erasure

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  16. ACaM: automated capability modeling for agent security

    PaperarXiv: 其他 AI 安全论文

  17. Training Language Models for Introspective Oversight

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  19. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  22. Examining retry transparency in agent tools

    PaperarXiv: 其他 AI 安全论文

  23. 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

  24. Agent-native applications: a new application paradigm

    PaperarXiv: 其他 AI 安全论文

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

    NewsTencent AI-Infra-Guard ReleasesTools

  26. 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

  27. 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

  28. Claude Fable 5.2 solved 80% of the 391 core tasks in the embodied robot evaluation in open-book mode, and only 47% in closed-book mode

    NewsWeChat · AI Era (Xinzhiyuan)AI updates

  29. A security vendor reveals the ARTEX attack incident response process: the AI agent launched the attack within minutes of obtaining an API key, and the defender used AI to accelerate the investigation

    NewsiThome (Taiwan)Event

  30. Brazil's Chamber of Deputies Bill PL 5792/2025 proposes using AI to automatically audit government procurement tenders and contracts

    Newscamara.leg.brGovernance

  31. Anthropic IPO priced at $83 per share; Reuters says subscription demand reached several times the offering size

    NewsWeChat · Synced (Jiqizhixin)AI updates

  32. Headwaters discloses internal practice of AI code defense: fully enables Claude Security, advances reasoning-based security

    NewsNo.1 PR TIMESTools

  33. Japan proposes Japan-ASEAN AI safety evaluation cooperation framework

    NewsMinistry of Foreign Affairs of JapanGovernance

  34. Google upgrades Gemini Tasks, first launching AI phone calls on the user's behalf and shopping payment features in the US, and opening it for free use for the first time

    NewsiThome (Taiwan)AI updates

  35. Resolution Hypothesis: the key to agent evolution is recognizing improvement

    PaperHugging Face Daily Papers

  36. Making samples sing in unison: mitigating spurious correlations via cross-view consensus

    PaperHugging Face Daily Papers

  37. Anthropic IPO priced at $83, total fundraising over $94 billion, a record

    NewsWeChat · QbitAIAI updates

  38. Summary of public consultation feedback on the Government of Canada's AI register: participants affirmed transparency and suggested usability improvements

    NewsIRCCGovernance

  39. Former NSC Director Tobin says Nvidia's influence on export control enforcement constitutes regulatory capture

    XX @themidasprojGovernance

  40. US GAO covert investigation: 4 major AI services including ChatGPT all generated information usable for attack planning in under 12 hours

    Newszaikei.co.jpEvaluation