Skip to content

Scan record

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

Nov 1738 loaded

  1. When backdoors can be switched off: suppression-aware backdoor attacks on vision-language-action models

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

  2. Building enterprise AI infrastructure: the evolution of the AI governance committee and the chief ethics officer role

    PaperarXiv: 其他 AI 安全论文

  3. BadGCL: Persistent Backdoor Attacks Against Graph Continual Learning Systems

    PaperarXiv: 其他 AI 安全论文

  4. Protecting the system while leaving users stranded: the limits of multi-agent authorization

    PaperarXiv: 其他 AI 安全论文

  5. Beyond Prompts: Runtime Contracts for Coding Agents

    PaperarXiv: 其他 AI 安全论文

  6. From facts to personas: interpretable persona unlearning in LLMs based on mixture of experts

    PaperarXiv: 其他 AI 安全论文

  7. Hardening agent network populations via multi-criteria competitive co-evolution: insights from wargame strategy optimization

    PaperarXiv: 其他 AI 安全论文

  8. Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers

    PaperarXiv: 其他 AI 安全论文

  9. Operating points of frozen guardrail probes fail under base model updates

    PaperarXiv: 其他 AI 安全论文

  10. On-Policy Distillation as a Backdoor Propagation Channel

    PaperarXiv: 其他 AI 安全论文

  11. A Bag of Concepts? Testing Role-Filler Bindings in the Verbalizable Workspace

    PaperarXiv: 其他 AI 安全论文

  12. Agent-ZTA: A Chain-Aware Zero-Trust Model for Bidirectional Security State Propagation and Runtime Containment in Multi-Agent Delegation

    PaperarXiv: 其他 AI 安全论文

  13. MemeEconomy: Will LLM agents trade ethics for survival?

    PaperarXiv: 其他 AI 安全论文

  14. Same Evidence, Different Verdicts: How Delivery of CT Images and DICOM Metadata Changes VLM Quality Control Decisions

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  17. Rethinking the Verification of Machine Unlearning

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  19. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    Newssooperset/mcp-atlassianEvent

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

    Newssooperset/mcp-atlassianEvent

  24. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  29. Attacker diversity reduction in adaptive LLM red teaming

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  32. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  35. 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

  36. InclusionMed: An AI benchmark for inclusive healthcare

    PaperHugging Face Daily Papers

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

    NewsPortal CMBHGovernance

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

    PaperHugging Face Daily Papers