AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration

Computer Science > Cryptography and Security [Submitted on 1 Apr 2026] AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration Ruhao Liu, Weiqi Huang, Qi Li, Xinchao Wang Membership Inference Attacks (MIAs) serve as a fundamental auditing tool for evaluating training data leakage in machine learning models. However, existing methodologies predominantly rely on static, handcrafted heuristics that lack adaptability, often leading to suboptimal performance when transferred across different large models. In this work, we propose AutoMIA, an agentic framework that reformulates membership inference as an automated process of self-exploration and strategy evolution. Given high-level scenario specifications, AutoMIA self-explores the attack space by generating executable logits-level strategies and progressively refining them through closed-loop evaluation feedback. By decoupling abstract strategy reasoning from low-level execution, our framework enables a systematic, model-agnostic traversal of the attack search space. Extensive experiments demonstrate that AutoMIA consistently matches or outperforms state-of-the-art baselines while eliminating the need for manual feature engineering. Subjects: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2604.01014 [cs.CR]   (or arXiv:2604.01014v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.01014 Focus to learn more Submission history From: Qi Li [view email] [v1] Wed, 1 Apr 2026 15:17:45 UTC (537 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)