Skip to content

Scan record

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

Nov 1739 loaded

  1. Quantum-Inspired Orthogonal Adapters for Certifiably Robust Medical Image Classification

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

  2. Not All Steps Matter: Time-Adaptive Spectral Control for Concept Removal in Diffusion Models

    PaperarXiv: 其他 AI 安全论文

  3. Rethinking the Verification of Machine Unlearning

    PaperarXiv: 其他 AI 安全论文

  4. When Helpful Agents Cause Economic Harm: Evaluating the Safety of LLM Agents in Executable Economic Worlds

    PaperarXiv: 其他 AI 安全论文

  5. NYUAD participates in the ArGuard shared task: a multimodal embedding model for detecting Arabic hateful memes and unsafe prompts

    PaperarXiv: 其他 AI 安全论文

  6. Jailbreaking LLMs with language style as a hidden attack surface

    PaperarXiv: 其他 AI 安全论文

  7. Endogenous preferences as vulnerability signals: discovering universal adversarial trigger words that degrade LLM utility

    PaperarXiv: 其他 AI 安全论文

  8. mcp-atlassian fixes a credential misuse vulnerability in which HTTP transport does not validate Host and Origin under specific configurations

    Newssooperset/mcp-atlassianEvent

  9. mcp-atlassian 0.24.5 concurrent Markdown writes may mix in content from other requests, fixed in 0.24.6

    Newssooperset/mcp-atlassianEvent

  10. We Hold All the Cards: Securing Agent Cards at the runtime trust boundary of the Agent2Agent protocol

    PaperarXiv: 其他 AI 安全论文

  11. When the spec sheet lies: injection attacks against LLM-generated compliance documents

    PaperarXiv: 其他 AI 安全论文

  12. Optional Traps: An Empirical Study of LLM Agents Facing Credential Deception and Alert-Driven Revocation

    PaperarXiv: 其他 AI 安全论文

  13. VAST: Compiling Real Vulnerability Scenarios into Verifiable Multi-Step Environments to Evaluate LLM Red-Team Agents

    PaperarXiv: 其他 AI 安全论文

  14. Agent Authenticator: Passkey-level hardware-bound authentication for AI agents

    PaperarXiv: 其他 AI 安全论文

  15. Attacker diversity reduction in adaptive LLM red teaming

    PaperarXiv: 其他 AI 安全论文

  16. Compositional Exploitation in Autonomous Coding Agents: Attack Mechanisms and Ad Hoc Defenses

    PaperarXiv: 其他 AI 安全论文

  17. Security of deep research agents: attack surface, defenses, benchmarks, and agenda seeding targeting research planning

    PaperarXiv: 其他 AI 安全论文

  18. Beyond Patches: Control-Gated Benign Probe Reconstruction of Patch Bypasses from Incomplete Fixes in LLM Agent Frameworks

    PaperarXiv: 其他 AI 安全论文

  19. AudioTrace: File-Level Membership Detection for Audio LLMs

    PaperarXiv: 其他 AI 安全论文

  20. Swarm Shepherd: Protecting Multi-Agent Ecosystems from Persistent Latent Intrusions

    PaperarXiv: 其他 AI 安全论文

  21. German research reveals that at least 7,403 databases of apps developed by users on the AI development platform Lovable have improper permission settings

    NewsiThome (Taiwan)Event

  22. InclusionMed: An AI benchmark for inclusive healthcare

    PaperHugging Face Daily Papers

  23. Belo Horizonte City Council to hold hearing on November 18 to discuss AI in public safety

    NewsPortal CMBHGovernance

  24. DominoBench: evaluating multi-step physical reasoning from static images

    PaperHugging Face Daily Papers

  25. SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

    PaperHugging Face Daily Papers

  26. Centered Ablation: why last-layer direction ablation is insufficient or collapses, and a closed-form correction

    PaperHugging Face Daily Papers

  27. A quick guide to data center construction ban litigation

    NewsFinancial Times · AIAI updates

  28. OpenAI uses AI to strengthen cyber defense for NATO and allied countries

    NewsOpenAIEvent

  29. According to sources, Nvidia warned chip buyers that remote access to AI chips from China may bring legal risks

    NewsCNBC · TechnologyGovernance

  30. Apollo Research member: training against CoT-like surfaces may be similar to training against CoT

    NewsLessWrongAlignment

  31. Australia and 10 other countries signed the US-led San Francisco Declaration to protect the sensitive technologies and supply chains needed for advanced AI

    NewsACSC (Australia)AI updates

  32. Helen Clark: Automated warfare has arrived, and governments must restrain it

    NewsThe Guardian · AIGovernance

  33. Hackers use AI to automate vulnerability research, and exploited zero-day vulnerabilities surge to 22 in a single month

    NewsiThome (Taiwan)Event

  34. OpenAI opens access to 4 external organizations to examine AI model safety in depth

    NewsiThome (Taiwan)Governance

  35. The U.S. Department of Commerce and the Department of Justice said that in 2024 they had opened an investigation into Nvidia partner Megaspeed

    NewsCNBC · TechnologyGovernance

  36. Google report: threat actors use AI to launch cyberattacks, often without human involvement

    NewsHindustan TimesEvent

  37. AI security accounts for more than one-third of cybersecurity seed-round financing deals

    NewsHelp Net Security AIAI updates

  38. K2-Horizon: an open-source language model frontier fleet

    PaperHugging Face Daily Papers

  39. Malware found in the @shadowdqj/image-mcp package

    NewsGitHub Security AdvisoriesEvent