attacks
4 notes, newest first.
Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
The research discusses the study of multi-agent AI control in real-world scenarios where multiple agents operate over shared infrastructure. The paper introduces FakeLab, a synthetic AI-lab codebase used to evaluate…
Agent Data Injection Attacks are Realistic Threats to AI Agents
A new type of attack called Agent Data Injection (ADI) has been introduced, which injects malicious data disguised as trusted data to make AI agents perform unintended actions. This type of attack can bypass existing…
Distributed Attacks in Persistent-State AI Control
Researchers explore the issue of distributed attacks on autonomous AI coding agents that persistently ship code iteratively. They introduce Iterative VibeCoding, a setting for studying AI control, where an AI agent…
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
The paper introduces ShareLock, a stealthy multi-tool threshold poisoning framework designed to exploit the interaction between Large Language Models (LLMs) and external tools through the Model Context Protocol (MCP)…
