AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
This enables non-experts like ML service providers and auditors to systematically assess risks without deep domain expertise, though it is incremental in applying LLM agents to a known problem.
The paper tackles the challenge of implementing inference attacks on ML services by introducing AttackPilot, an autonomous agent that uses LLMs to conduct these attacks without human intervention, achieving a 100.0% task completion rate and near-expert performance with an average cost of $0.627 per run.
Inference attacks have been widely studied and offer a systematic risk assessment of ML services; however, their implementation and the attack parameters for optimal estimation are challenging for non-experts. The emergence of advanced large language models presents a promising yet largely unexplored opportunity to develop autonomous agents as inference attack experts, helping address this challenge. In this paper, we propose AttackPilot, an autonomous agent capable of independently conducting inference attacks without human intervention. We evaluate it on 20 target services. The evaluation shows that our agent, using GPT-4o, achieves a 100.0% task completion rate and near-expert attack performance, with an average token cost of only $0.627 per run. The agent can also be powered by many other representative LLMs and can adaptively optimize its strategy under service constraints. We further perform trace analysis, demonstrating that design choices, such as a multi-agent framework and task-specific action spaces, effectively mitigate errors such as bad plans, inability to follow instructions, task context loss, and hallucinations. We anticipate that such agents could empower non-expert ML service providers, auditors, or regulators to systematically assess the risks of ML services without requiring deep domain expertise.