MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, s
2026-10-22 归档
今日共收录 1761 条安全情报，包含 937 个 CVE，415 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory
Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes i
ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents
AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that
Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity Contexts
LLMs increasingly operate over mixed-sensitivity contexts, where they must reason over information ranging from public t
Raise or Check? Predicting the Necessity of Additional Fuzzing for Continuous Fuzzing
Continuous fuzzing is used for vulnerability detection in Open Source Software (OSS). Large-scale services such as Googl
HydraPoT: A Configurable Multi-Agent Framework for Cost-Aware LLM-Assisted Honeypots
Large language models (LLMs) can improve honeypot realism by generating dynamic, context-aware responses, but powerful c
Local Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents
Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolatio
The Show-Up Attack: When Subagents Win Over Their Supervisor
Multi-agent systems are increasingly deployed to coordinate multiple large language model (LLM) agents. However, this al
Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment
When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user grants. Existi
Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness
Beneath the apparent diversity of foundation models lies an increasingly homogeneous technical stack of common training
Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages
Large language models are deployed globally, yet safety alignment and evaluation remain concentrated in English: harmful
Guided Diffusion for Trustworthy Synthetic Text Generation
The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks
When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs
Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remain
Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference
Personalized large language models (LLMs) increasingly rely on profile-conditioned inference, pairing public requests wi
You Are the Trigger: Speaker-Activated Backdoors
Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing au
Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams
Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermea
Beyond Attack Success Rate: Cost-Aware Metric for Evaluating Iterative LLM Jailbreaks
Attack success rate (ASR) evaluates jailbreaks against large language models without accounting for repeated calls to th
Fake News, Real Crashes: Information Injection Attacks on LLM Financial Trading Agents
Large language model (LLM) agents now trade real capital using news as evidence, yet they cannot reliably tell fabricate
[原创]CVE-2020-6507利用链
CVE-2020-6507
[原创]CVE-2020-6507利用链
CVE-2026-39821：Go idna 纯 ASCII 标签解码漏报
CVE-2026-39821
CVE-2026-39821：Go idna 纯 ASCII 标签解码漏报