Skip to content

Scan record

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

Nov 1738 loaded

  1. Can AI judge you? An empirical audit of the deployment readiness of LLM-assisted hiring systems

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

  2. "Don't leave the task unfinished": persistence-driven violations under silent supervision

    PaperarXiv: 其他 AI 安全论文

  3. HalluProbe: using VLM hallucinations for backdoor detection

    PaperarXiv: 其他 AI 安全论文

  4. Where in multimodal LM-derived models can Rank-1 DiM refusal be intervened on?

    PaperarXiv: 其他 AI 安全论文

  5. Fine-Grained RLAIF for Visual Safety: Learning to Magnify Hazards for Multimodal Safety Alignment

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  7. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  10. Beyond Prompts: Runtime Contracts for Coding Agents

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  15. On-Policy Distillation as a Backdoor Propagation Channel

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  17. 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

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

    PaperarXiv: 其他 AI 安全论文

  19. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  22. Rethinking the Verification of Machine Unlearning

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  24. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    Newssooperset/mcp-atlassianEvent

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

    Newssooperset/mcp-atlassianEvent

  29. 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

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  34. Attacker diversity reduction in adaptive LLM red teaming

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

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

    PaperarXiv: 其他 AI 安全论文

  37. 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

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

    PaperarXiv: 其他 AI 安全论文