Scan record
Nov 1738 loaded
- Beyond Prompts: Runtime Contracts for Coding Agents
PaperarXiv: 其他 AI 安全论文The item you came from
- From facts to personas: interpretable persona unlearning in LLMs based on mixture of experts
PaperarXiv: 其他 AI 安全论文
- Hardening agent network populations via multi-criteria competitive co-evolution: insights from wargame strategy optimization
PaperarXiv: 其他 AI 安全论文
- Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers
PaperarXiv: 其他 AI 安全论文
- Operating points of frozen guardrail probes fail under base model updates
PaperarXiv: 其他 AI 安全论文
- On-Policy Distillation as a Backdoor Propagation Channel
PaperarXiv: 其他 AI 安全论文
- A Bag of Concepts? Testing Role-Filler Bindings in the Verbalizable Workspace
PaperarXiv: 其他 AI 安全论文
- 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
- MemeEconomy: Will LLM agents trade ethics for survival?
PaperarXiv: 其他 AI 安全论文
- 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
- Quantum-Inspired Orthogonal Adapters for Certifiably Robust Medical Image Classification
PaperarXiv: 其他 AI 安全论文
- Not All Steps Matter: Time-Adaptive Spectral Control for Concept Removal in Diffusion Models
PaperarXiv: 其他 AI 安全论文
- Rethinking the Verification of Machine Unlearning
PaperarXiv: 其他 AI 安全论文
- When Helpful Agents Cause Economic Harm: Evaluating the Safety of LLM Agents in Executable Economic Worlds
PaperarXiv: 其他 AI 安全论文
- 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
- Jailbreaking LLMs with language style as a hidden attack surface
PaperarXiv: 其他 AI 安全论文
- Endogenous preferences as vulnerability signals: discovering universal adversarial trigger words that degrade LLM utility
PaperarXiv: 其他 AI 安全论文
- mcp-atlassian fixes a credential misuse vulnerability in which HTTP transport does not validate Host and Origin under specific configurations
Newssooperset/mcp-atlassianEvent
- mcp-atlassian 0.24.5 concurrent Markdown writes may mix in content from other requests, fixed in 0.24.6
Newssooperset/mcp-atlassianEvent
- 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
- When the spec sheet lies: injection attacks against LLM-generated compliance documents
PaperarXiv: 其他 AI 安全论文
- Optional Traps: An Empirical Study of LLM Agents Facing Credential Deception and Alert-Driven Revocation
PaperarXiv: 其他 AI 安全论文
- VAST: Compiling Real Vulnerability Scenarios into Verifiable Multi-Step Environments to Evaluate LLM Red-Team Agents
PaperarXiv: 其他 AI 安全论文
- Agent Authenticator: Passkey-level hardware-bound authentication for AI agents
PaperarXiv: 其他 AI 安全论文
- Attacker diversity reduction in adaptive LLM red teaming
PaperarXiv: 其他 AI 安全论文
- Compositional Exploitation in Autonomous Coding Agents: Attack Mechanisms and Ad Hoc Defenses
PaperarXiv: 其他 AI 安全论文
- Security of deep research agents: attack surface, defenses, benchmarks, and agenda seeding targeting research planning
PaperarXiv: 其他 AI 安全论文
- 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
- AudioTrace: File-Level Membership Detection for Audio LLMs
PaperarXiv: 其他 AI 安全论文
- Swarm Shepherd: Protecting Multi-Agent Ecosystems from Persistent Latent Intrusions
PaperarXiv: 其他 AI 安全论文
- German research reveals that at least 7,403 databases of apps developed by users on the AI development platform Lovable have improper permission settings
NewsiThome (Taiwan)Event
- InclusionMed: An AI benchmark for inclusive healthcare
PaperHugging Face Daily Papers
- Belo Horizonte City Council to hold hearing on November 18 to discuss AI in public safety
NewsPortal CMBHGovernance
- DominoBench: evaluating multi-step physical reasoning from static images
PaperHugging Face Daily Papers
- SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations
PaperHugging Face Daily Papers
- Centered Ablation: why last-layer direction ablation is insufficient or collapses, and a closed-form correction
PaperHugging Face Daily Papers
- A quick guide to data center construction ban litigation
NewsFinancial Times · AIAI updates
- OpenAI uses AI to strengthen cyber defense for NATO and allied countries
NewsOpenAIEvent