Poisoned Skills: Propagating Jailbreaks Through Agent Markdown Files
Modern agent frameworks allow users to provide Markdown files containing system prompts, tool descriptions, and skill de
#cs.AI
共收录 1652 条相关情报。
← 返回所有主题Constraining the Commit Boundary: A DIO/ODI-Informed Authorization Guardrail for Agentic Entity Resolution
Agentic Entity Resolution (ER) systems iteratively plan actions, retrieve evidence, revise hypotheses, and propose graph
When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning
Multi-relational graph detectors learn from clean data how much to trust each relation, but an adversary pays a differen
When Skills Tell Agents Not to Ask: A Large-Scale Study of Oversight Directives in Agent Skills
Agent skills, reusable instruction packages centred on a SKILL.md file, extend AI agents on demand, and a single line in
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
FVH-Bench: Evaluating Image Generator Safety Beyond Overtly Harmful Imagery
Modern image generators can produce complex visual artifacts, including diagrams, interfaces, and records that combine t
CASEL: Consequence-Aware Selective Execution for Reliable Long-Horizon Tool-Using Agents
Tool-using language agents increasingly modify external systems, yet most runtime safeguards allocate scrutiny by generi
FIDES-Live: Evaluating Behavioral Concordance in Sequential Trading Agents
Sequential trading agents produce decisions, orders, execution receipts, account states, and reports that need not agree
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
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
I-HITL: Inalienable Human-in-the-Loop
Human oversight is a pillar of AI safety. It is often exercised by a human in the loop (HITL) who approves critical acti
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
The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
Web services increasingly expose backend interfaces that let users delegate tasks to AI agents, which invoke service ope
JANUS: Synthesizing Cross-Layer Defenses Against Web Deserialization Attacks
Unsafe deserialization turns untrusted data into attacker-controlled execution, and a single vulnerability can admit div
Pricing Cross-Bank Context in Federated Anti-Money Laundering
Most graph-based Anti-Money Laundering (AML) methods assume access to a pooled transaction graph containing all accounts
Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges
AI systems built around large models increasingly use experience and feedback to make persistent changes to models, prom
SoK: Timestamps Are Not a Time Model: Rethinking Temporal Reasoning in Host-Based Intrusion Detection
Host-based intrusion detectors order events, window audit streams and sequence attack stages by their timestamps. Every
CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems
Agent Skills allow LLM agents to combine reusable capabilities, but checking each Skill in isolation cannot rule out pol
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