ACL Findings2026
InferPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
Yixin Wu, Rui Wen, Chi Cui, Michael Backes, Yang Zhang
Abstract
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 InferPilot, 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. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Membership Inference Attacks Against Machine Learning Models cites Stealing Machine Learning Models via Prediction APIs
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering cites SWE-bench: Can Language Models Resolve Real-world Github Issues?
Builds on28
- Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, David A. WagnerS&P 2017 · 9,786 citations
- Membership Inference Attacks Against Machine Learning ModelsReza Shokri, Marco Stronati, Congzheng Song, Vitaly ShmatikovS&P 2017 · 5,137 citations
- Stealing Machine Learning Models via Prediction APIsFlorian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter et al.USENIX Security 2016 · 2,088 citations
- SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao et al.ICLR 2024 · 2,082 citations
- SWE-agent: Agent-Computer Interfaces Enable Automated Software EngineeringJohn Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.NeurIPS 2024 · 2,059 citations
Related papers
- LLM-Pilot: Characterize and Optimize Performance of your LLM Inference ServicesMalgorzata Lazuka, Andreea Anghel, Thomas P. ParnellSC 2024 · 17 citations
- InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model AgentsQiusi Zhan, Zhixiang Liang, Zifan Ying, Daniel KangACL Findings 2024 · 147 citations
- InferCept: Efficient Intercept Support for Augmented Large Language Model InferenceReyna Abhyankar, Zijian He, Vikranth Srivatsa, Hao Zhang et al.ICML 2024 · 29 citations
- Automated Profile Inference with Language Model AgentsYuntao Du, Zitao Li, Bolin Ding, Yaliang Li et al.ACL Findings 2026
- BadAgent: Inserting and Activating Backdoor Attacks in LLM AgentsYifei Wang, Dizhan Xue, Shengjie Zhang, Shengsheng QianACL 2024
