The Envelope Layer: An Underestimated Surface of LLM Agent Defense
Prior work framed the envelope layer as the channel through which malicious content enters an agent, and established it
2026-10-28 归档
今日共收录 2009 条安全情报，包含 1141 个 CVE，471 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Watermark Basins: Black-Box Detection of Distilled LLMs
Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trai
Blindfold: Keeping the Audit Coin Secret from LLM Agents
Audit-based certification bounds the violation rate of an LLM agent by auditing a random fraction $\varepsilon$ of actio
PrivacyEvalClaw: A Tool-Augmented Deliberative Agent for Auditing Privacy Leakage in LLM Jailbreak Responses
Reliable evaluation is a critical bottleneck in privacy red-teaming of large language models (LLMs): determining whether
What Victims Take Away: Attack Reuse and Defense Revision after Prompt-Injection Attacks
Attack logs and red-team reports show targets the attacks used against them, to help them repair their defenses. Prompt
Detecting and Mitigating Query-Based System Prompt Leakage Attacks
Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access
BUSTA: Teaching Small Language Models to Reason About Binary Execution
Large Language Models (LLM) are increasingly applied to Reverse Engineering (RE) workflows. RE, however, differs from co
Bringing Hardware Security Education to All: A Seamless Curriculum Integration Approach
Cybersecurity education has predominantly focused on software and network security, under the assumption that the underl
Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol
LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadat
Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models
A vulnerability costs more to fix the later it is discovered. As coding agents generate code faster than developers can
Adversary Brains: Hypothesis-Based Logical Signatures for Threat Actor Detection with LLMs
An adversary brain is an LLM-based model of a threat actor's behavior, held as an evolving logical signature: a hypothes
Then there is prompt injection, a malicious email, ...: The Wild Wide West of OpenClaw Agentic System Security
AI-powered personal assistant frameworks such as OpenClaw combine LLM reasoning, persistent memory, tool invocation, loc
Can Open Be Too Open? On the Security and Trustworthiness of Fully Transparent LLMs
There are different levels of transparency for LLMs: open weights, open data, and/or open pipeline. Recently, more inter
GuardRAG: A Post-Retrieval Defense against Poisoning Attacks in Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models (LLMs) by incorporating ext
Steering for Safety, Hijacking for Profit: Trojan Threats in the LLM Activation Steering Supply Chain
As large language models (LLMs) are increasingly integrated into Web search, online recommendation, and intelligent deci
The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming
Automatic red teaming increasingly relies on large language models (LLMs) to iteratively diagnose failed attacks and pro
Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition
This paper introduces Scope-Gap Injection (SGI), an indirect prompt injection method for multi-stage LLM-agent safety pi
From Representations to Computational Trajectories: Intrinsic Fingerprinting for Large Language Model Provenance Verification
Large language models (LLMs) are valuable digital assets, yet their weights can be easily modified after unauthorized ac
SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments
Large language model (LLM) agents are increasingly wired to consequential tools that send public alerts, dispatch respon
SymLift: Neural Semantic Lifting for Compile-Free Vulnerability Detection in Context-Incomplete Code Fragments
Missing project context can prevent build-dependent analyzers from constructing program relations required for vulnerabi