Scan record
Yesterday · Nov 1940 loaded
- Microsoft agent-framework PyPI package poisoned
NewsStepSecurityEventThe item you came from
- When figures and text disagree: evaluating autonomous visual evidence verification in scientific papers
PaperarXiv
- Semantics-aware contrastive and explicitly disentangled representations for AI-generated video detection
PaperarXiv
- Log analysis for LLM agents: a lifecycle-oriented survey
PaperarXiv
- IIJ Global and VeriCerts launch advertising trust gateway PoC: verifying ad issuers and tampering via DID/VC
NewsIIJ Global SolutionsAI updates
- LLM jailbreak detection based on contrastive prototype structure
PaperarXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses
- George Monbiot commentary: The UK growth plan forces through data centers nobody wants, betting that the AI bubble won't burst
NewsThe Guardian · AIGovernance
- Researchers propose inducing monitorable reward hacking to compensate for the failure of gradient routing
NewsLessWrongAlignment
- A LessWrong author posted about protesting Anthropic's IPO on November 19, calling for a ban on recursive self-improvement
NewsLessWrongGovernance
- Shanghai AI Lab paper: switch to a different agent execution framework, and model score rankings may reverse
NewsWeChat · Weijiqi LixinAI updates
- Tencent Zhuque Lab open-sources the pikit toolbox to systematically evaluate AI agent indirect prompt injection risk
NewsWeChat · Weijiqi LixinTools
- Beihang and Alibaba teams propose the PASP framework, using multi-perception views and adversarial self-play to improve large models' ability to recognize disguised harmful content
NewsWeChat · Weijiqi LixinDefenses
- Paper: under ANCHOR multi-turn attacks, refusal rates of 8 CLI agents drop to 0%
NewsWeChat · Weijiqi LixinAttacks
- Xint discloses 5 Nginx RCE vulnerabilities, four discovered by automation
NewsWeChat · SecureNexusLabEvent
- OpenAI is testing giving its autonomous agent Dots its own email address
NewsiThome (Taiwan)AI updates
- Solomonoff induction based on reflective oracles
NewsAI Alignment ForumAlignment
- CCN updates ENS information security policy and responsibilities and functions guidance, adding an appendix linking data protection and AI rules
NewsCentro Criptológico NacionalGovernance
- Can you make a model believe false facts in the prompt?
PaperarXiv: Alignment, Deception & Oversight
- Dependency fabrication in repository deployment agents
PaperarXiv: Alignment, Deception & Oversight
- Nudge Security report: AI agents inherit employee access permissions, and their use is unsupervised
NewsHelp Net Security AIEvent
- Negotiating control and accountability among stakeholders in high-risk AI application scenarios: development and evaluation of the ALIGN method
PaperarXiv: 其他 AI 安全论文
- RECLAIM: robot vision-guided adversarial patch defense via embodied attention feedback
PaperarXiv: 其他 AI 安全论文
- Truthgate: Checking coding agents' behavior against records they cannot edit—cheating, deterrence and disclosure on impossible tasks
PaperarXiv: 其他 AI 安全论文
- PGPO: prototype-guided progressive obfuscation for privacy-preserving LLM-enhanced recommendation
PaperarXiv: 其他 AI 安全论文
- Kaer: safety-aware replanning for multi-agent systems
PaperarXiv: 其他 AI 安全论文
- Exactly stealing other clients' training data in federated learning
PaperarXiv: 其他 AI 安全论文
- The limitation is in the input, not the model: state-dependent command safety in natural language interfaces for industrial controllers
PaperarXiv: 其他 AI 安全论文
- Gradient-based defensive poisoning against system identification attacks on cyber-physical systems
PaperarXiv: 其他 AI 安全论文
- GateWatch: Low-overhead LLM monitoring with Boolean circuits
PaperarXiv: 其他 AI 安全论文
- SCR: Detecting Backdoor-Poisoned Samples via Clean Reference Residuals
PaperarXiv: 其他 AI 安全论文
- Probing agent over-proactiveness in real-world settings with Continuation Audits
PaperarXiv: 其他 AI 安全论文
- Nothing to Declare: Steering a Single Neuron Increases Concealment in Agent Teams
PaperarXiv: 其他 AI 安全论文
- PIPETTE: prompt injection purple teaming for robust LLM agents
PaperarXiv: 其他 AI 安全论文
- Can Weight-Space Programming Change a Model's Learned Ethical Priorities?
PaperarXiv: 其他 AI 安全论文
- AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents
PaperarXiv: 其他 AI 安全论文
- When shuffling fails: recovering tokens from obfuscated KV caches
PaperarXiv: 其他 AI 安全论文
- What survives in the shift from text to pixels? Conditional protection against prompt injection in documents rendered as images
PaperarXiv: 其他 AI 安全论文
- Learning to Coordinate: LLM-Guided Workflow Evolution for Token-Efficient Red Teaming
PaperarXiv: 其他 AI 安全论文
- Guarding the kingdom of skilled agents in a computational AI dynasty: control-flow integrity for agent skills
PaperarXiv: 其他 AI 安全论文
- VESPA: Verifiable Symbolic Policy Adaptation for Safe Reinforcement Learning
PaperarXiv: 其他 AI 安全论文