Scan record
Nov 1639 loaded
- Causal AI-driven secure millimeter-wave beam alignment based on a defensive variational autoencoder
PaperarXiv: 其他 AI 安全论文The item you came from
- The Right Tokens, the Right Time: From Per-Token Gating to Trajectory-Aware Activation Steering
PaperarXiv: 其他 AI 安全论文
- From Bytes to Behavior: Request-Level Attribution from Hidden States of Running GPUs
PaperarXiv: 其他 AI 安全论文
- LLM puts the existential risk of AI at 10%
PaperarXiv: 其他 AI 安全论文
- Forget the lineage: forward-secure, lineage-complete cryptographic erasure for LLM agent memory
PaperarXiv: 其他 AI 安全论文
- Reasoning Models Confabulate Explanations to Defend Injected Beliefs About Their Own Requests
PaperarXiv: 其他 AI 安全论文
- Adversarial attacks on symbolic vocabulary vulnerabilities in LLM planners
PaperarXiv: 其他 AI 安全论文
- Cracks in the Embedding: Robustness and Stability of JEPA-Based Chest X-ray Representations
PaperarXiv: 其他 AI 安全论文
- Soteria: Formally Verified Planning and Runtime Enforcement for Safe LLM Agents
PaperarXiv: 其他 AI 安全论文
- Anti-distillation is cheap: lightweight distillation resistance via style disruption
PaperarXiv: 其他 AI 安全论文
- Auditing Chatbots' Encroachment into the Professional Legal Practice Domain
PaperarXiv: 其他 AI 安全论文
- Safety side effects of preventive personality steering: an empirical audit
PaperarXiv: 其他 AI 安全论文
- System security is only as strong as the weakest agent: an attack that occurs only in multi-agent systems
PaperarXiv: 其他 AI 安全论文
- Pushing Down the Mountain: The Effect of Framing Effects and Internal State Interventions on Collusive Behavior of Long-Horizon LLM Agents
PaperarXiv: 其他 AI 安全论文
- Adversarial tracking: attacks on image sensors for autonomous vehicle object tracking
PaperarXiv: 其他 AI 安全论文
- Unfinished-Bench: Measuring Rule-Violating Behavior of Persistent Agents in Real Work Environments
PaperarXiv: 其他 AI 安全论文
- Physical Attacks on End-to-End Autoencoder-Based Communications via Evolutionary Transfer Learning
PaperarXiv: 其他 AI 安全论文
- Google Project Zero will shorten vulnerability disclosure deadlines in stages: 60 days starting in 2027, 30 days starting in 2028
NewsiThome (Taiwan)Governance
- New York Times: Lutnick family business's ties to Malaysian data centers raise conflict-of-interest questions
NewsSeoul Economic DailyGovernance
- 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
- 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
- AI cheating suspicions spread, calls emerge in multiple South Korean national exams to verify high scorers
NewsChosunBizEvent
- South Korean prime minister asks for study on shutting down Wi-Fi at CSAT exam venues to prevent AI cheating
NewsYonhapEvent
- Indian officials say India is less concerned about AI threats than the United States
NewsSemaforAI updates
- Taiwan's deputy digital minister on the Jensen Huang scandal: "We feel sad"
NewsSemaforGovernance
- A generalizable safety-aware robot behavior planning method based on an explicit constraint space
PaperarXiv
- Adaptable Watermarking: Transforming Image Watermarking Models via Lightweight Adapters
PaperarXiv
- VLAN: Vision-Language Accessible Navigation
PaperarXiv
- Securing Multi-Agent Systems by Design
PaperarXiv
- An operational definition of opaque serial depth
PaperarXiv
- Beyond Attack-Based Accuracy: Rethinking Adversarial Robustness Evaluation via Structural Gradient Alignment
PaperarXiv
- Decoupling Forgetting and Utility: Lightweight LLM Unlearning via Orthogonal Null-Space Projection
PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses
- 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
- Constructing a steering vector via input optimization
PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses
- Alignment via Reflect-Reasoning: Learning How to Follow Principles
PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses
- FT Lex commentary: publishers are capable of a tough contest with big tech companies
NewsFinancial Times · AIAI updates
- Former Nvidia chief Jensen Huang steps down in disgrace, dealing a blow to "open" models, with Anthropic and OpenAI benefiting
NewsFinancial Times · AIAI updates
- Japan plans to regulate unauthorized commercial use of AI to replicate celebrities' voices and likenesses
Newskmkj.krGovernance
- OpenAI Foundation board member says AI incidents will become the most likely cause of human death, warns of AI losing control
NewsSegye IlboOpinion