Skip to content

Scan record

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

Nov 1739 loaded

  1. EU scientific advisory bodies propose four AI regulatory recommendations

    Newswedoany.comGovernanceThe item you came from

  2. Cisco Talos discloses how hackers use ARTEX, PentAGI and HexStrike AI to automate cyberattacks

    NewsCybersecuritynewsEvent

  3. Microsoft's guide to defending against indirect prompt injection attacks: defense in depth with multiple layers of mitigations

    NewsMicrosoftDefenses

  4. NSFOCUS Technology's Fengyun Wei foundation model tops the CyberGym Model leaderboard with a 91.31% task success rate

    News绿盟科技技术博客Evaluation

  5. Amid fallout from Jensen Huang's resignation, Nvidia falls 0.56% premarket ahead of earnings

    NewsCNBC · TechnologyAI updates

  6. How VLMs plan their next step

    PaperarXiv

  7. Differentiable Exact Learning

    PaperarXiv

  8. Recovery Goes Too Far: Understanding and Fixing Risky Fallback in LLM Agents

    PaperarXiv

  9. Self-evolving dual-role deliberation for medication recommendation based on clinical records

    PaperarXiv

  10. ASCG: Adaptive Spatial Classifier Guidance for Precise Concept Suppression in Diffusion Models

    PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses

  11. Polish social media misogynistic speech detection dataset: transferability of hate speech detection from generic to specific hate types

    PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses

  12. Between the Lines: Contextual Investment Advice Detection in Multi-Turn Conversations

    PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses

  13. South Korean prosecutors seek three-year sentence in second instance of Chinese national graduate student deepfake sexual crime case

    NewsYonhapEvent

  14. Guatemala launches multi-stakeholder discussions to jointly develop a national artificial intelligence strategy

    Newsprensa.gob.gtAI updates

  15. Irene Liu on why California leads US frontier AI regulation: from the vetoed SB 1047 to SB 53

    NewsThe EU AI Act NewsletterGovernance

  16. An overview of AI safety in California state politics

    NewsLessWrongGovernance

  17. Rumored November 17 global blackout: a mix of distorted facts and fabricated videos

    NewsRTVEEvent

  18. British actors will gain more digital replica rights under an AI protection agreement with producers

    NewsThe Guardian · AIGovernance

  19. Backdoor trigger words are clearly readable in fine-tuned weights

    PaperarXiv: Adversarial Attacks, Backdoors & Poisoning

  20. Conv-Reluplex: A Verification Framework for Convolutional Neural Networks

    PaperarXiv: Adversarial Attacks, Backdoors & Poisoning

  21. Forging a Bearer to take over a LiteLLM MCP session: reproduction and analysis of the OAuth2 passthrough authentication bypass

    NewsXianzhi Community (Aliyun)Event

  22. NATO AI cyber defense uses up to 300B OpenAI tokens per month

    NewsHelp Net Security AIEvent

  23. Google finds AI agents writing and launching exploits without human involvement

    NewsHelp Net Security AIEvent

  24. CuRSE-Bench: A benchmark for probing cultural blind spots in text-to-image safety evaluation

    PaperarXiv: Dangerous Capabilities & Safety Evals

  25. Between Rigor and Reality: How AI Safety Benchmark Developers Understand Benchmark Use and Maintenance

    PaperarXiv: Alignment, Deception & Oversight

  26. Manipulating Bayesian inference and decision-making through data poisoning

    PaperarXiv: 其他 AI 安全论文

  27. Robustness as a Transferable Skill: Cross-Task Adversarial Defense for Vision-Language-Action Policies

    PaperarXiv: 其他 AI 安全论文

  28. The Paradox of Provenance and Privacy: Can Private Cloud Compute (PCC) Prove That Apple Reference Images Are Not Used for Learning?

    PaperarXiv: 其他 AI 安全论文

  29. When tool names are not identity: measuring provider misbinding in MCP-based AI agents

    PaperarXiv: 其他 AI 安全论文

  30. Optimistic verifiers get gamed: reward hacking under exact process oracles

    PaperarXiv: 其他 AI 安全论文

  31. Similar in Safety, Silent in Propagation: Limitations of Text-Similarity Guardrails for AI Agent Security

    PaperarXiv: 其他 AI 安全论文

  32. Evaluating Authorization and Trust Boundaries in Agent Orchestration Frameworks

    PaperarXiv: 其他 AI 安全论文

  33. Jev-as-a-Reward: Validating a Probabilistic Safety Judge for Reinforcement Learning

    PaperarXiv: 其他 AI 安全论文

  34. Experience Rot: Experienced agents fail where novices succeed

    PaperarXiv: 其他 AI 安全论文

  35. Which AI Use Cases Are Worth Piloting? A Risk and Value Framework for Funding, Scoping and Scaling AI

    PaperarXiv: 其他 AI 安全论文

  36. Tight PAC-Bayes Generalization Guarantees for LLM Judges

    PaperarXiv: 其他 AI 安全论文

  37. STA: A Split Temporal Adversarial Method for Evaluating the Robustness of Multimodal Reinforcement Learning Driving Policies

    PaperarXiv: 其他 AI 安全论文

  38. LEAF-OPD: Learning to Unlearn from Privileged Context via On-Policy Distillation

    PaperarXiv: 其他 AI 安全论文

  39. Who Bears the Excess Authority? Attributing AI Agent Behavior to the Delegating Party

    PaperarXiv: 其他 AI 安全论文