Skip to content

Scan record

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

Nov 1639 loaded

  1. Unfinished-Bench: Measuring Rule-Violating Behavior of Persistent Agents in Real Work Environments

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

  2. Physical Attacks on End-to-End Autoencoder-Based Communications via Evolutionary Transfer Learning

    PaperarXiv: 其他 AI 安全论文

  3. Google Project Zero will shorten vulnerability disclosure deadlines in stages: 60 days starting in 2027, 30 days starting in 2028

    NewsiThome (Taiwan)Governance

  4. New York Times: Lutnick family business's ties to Malaysian data centers raise conflict-of-interest questions

    NewsSeoul Economic DailyGovernance

  5. Cheating in China's college entrance exam can carry a maximum sentence of 7 years in prison; AI question-solving features suspended during exams

    NewsSeoul Economic DailyEvent

  6. Top scorer in South Korea's tax accountant exam admits to cheating with a miniature camera and generative AI and turns himself in

    NewsFinancial News KoreaEvent

  7. AI cheating suspicions spread, calls emerge in multiple South Korean national exams to verify high scorers

    NewsChosunBizEvent

  8. South Korean prime minister asks for study on shutting down Wi-Fi at CSAT exam venues to prevent AI cheating

    NewsYonhapEvent

  9. Indian officials say India is less concerned about AI threats than the United States

    NewsSemaforAI updates

  10. Taiwan's deputy digital minister on the Jensen Huang scandal: "We feel sad"

    NewsSemaforGovernance

  11. A generalizable safety-aware robot behavior planning method based on an explicit constraint space

    PaperarXiv

  12. Adaptable Watermarking: Transforming Image Watermarking Models via Lightweight Adapters

    PaperarXiv

  13. VLAN: Vision-Language Accessible Navigation

    PaperarXiv

  14. Securing Multi-Agent Systems by Design

    PaperarXiv

  15. An operational definition of opaque serial depth

    PaperarXiv

  16. Beyond Attack-Based Accuracy: Rethinking Adversarial Robustness Evaluation via Structural Gradient Alignment

    PaperarXiv

  17. Decoupling Forgetting and Utility: Lightweight LLM Unlearning via Orthogonal Null-Space Projection

    PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses

  18. Has Abliteration Become Harder? Not Consistently: Direction-Based Ablation and ARA for Refusal Removal in Qwen3.8, Gemma 4, Olmo 3.1 and Mistral Small 3.2 LLMs and Their Predecessors in Heretic

    PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses

  19. Constructing a steering vector via input optimization

    PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses

  20. Alignment via Reflect-Reasoning: Learning How to Follow Principles

    PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses

  21. FT Lex commentary: publishers are capable of a tough contest with big tech companies

    NewsFinancial Times · AIAI updates

  22. Former Nvidia chief Jensen Huang steps down in disgrace, dealing a blow to "open" models, with Anthropic and OpenAI benefiting

    NewsFinancial Times · AIAI updates

  23. Japan plans to regulate unauthorized commercial use of AI to replicate celebrities' voices and likenesses

    Newskmkj.krGovernance

  24. OpenAI Foundation board member says AI incidents will become the most likely cause of human death, warns of AI losing control

    NewsSegye IlboOpinion

  25. US Commerce Secretary Lutnick reportedly clears AI chips and advocates lax regulation, possibly involving family business interests in Southeast Asia

    Newsglobal.hk01.comGovernance

  26. Korean Association of Tax Accountants says practical training for trainee tax accountants will introduce assessments without AI assistance

    NewsFinancial News KoreaEvent

  27. Online post claims to have used AI to cheat into medical school; anxiety rises ahead of Korea's Suneung

    NewsSBSEvent

  28. Korean police seize devices including a micro camera in the AI cheating case involving the top scorer in the tax accountant exam, and are expected to summon him soon

    NewsSBSEvent

  29. Korean government to form interagency emergency team to prevent AI cheating on the College Scholastic Ability Test

    NewsKorea JoongAng DailyEvent

  30. Anonymous internet user posts claiming to have cheated with AI on Korea's Suneung as early as 2024, prompting calls to postpone the exam

    NewsThe Korea HeraldEvent

  31. Fed financial stability report warns of AI-related risks: forward leases and backstop guarantees for data center construction have reached about 3 trillion dollars

    News澎湃新闻 · 检索「AI风险」AI updates

  32. Jacob Helberg, U.S. Deputy Secretary of State for Economic Affairs, said the government needs to better explain the benefits of AI to the public

    NewsSemaforAI updates

  33. A LessWrong user attends a Boston AI protest with family, calling for regulation of AI

    NewsLessWrongGovernance

  34. Can LLMs Write Backdoors? An Empirical Security Study of Weight-Space Programming

    PaperarXiv

  35. Binarization as an attack surface of weightless neural networks

    PaperarXiv: 其他 AI 安全论文

  36. LLMs are vulnerable to malicious requests whose intent is hard to distinguish

    PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses

  37. Representational geometry as a diagnostic tool for adversarial robustness

    PaperarXiv: 其他 AI 安全论文

  38. Forescout researchers used AI to discover security vulnerabilities in discontinued devices that no one is patching

    NewsHelp Net Security AIAttacks

  39. Western Cape Department of Infrastructure (DOI) and AIFOD explore responsible AI in infrastructure

    NewsWCGAI updates