AutoMIA：通过代理自我探索改进的成员推断攻击基线
AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration
AI总结：
AutoMIA通过代理自我探索和策略进化，改进成员推断攻击基线，实现模型无关的攻击空间系统遍历，优于现有方法且无需手动特征工程。
摘要：
成员推断攻击（MIAs）是评估机器学习模型训练数据泄露的基本审计工具。然而，现有方法主要依赖静态手工设计的启发式方法，缺乏适应性，常在跨不同大型模型转移时表现不佳。本文提出AutoMIA，一种代理框架，将成员推断重新表述为自动化的自我探索和策略进化过程。给定高层场景规范，AutoMIA通过生成可执行的logits级策略并逐步通过闭环评估反馈进行优化，通过解耦抽象策略推理与低层执行，使框架能够系统地、模型无关地遍历攻击搜索空间。大量实验表明，AutoMIA一致匹配或优于现有最佳基线，同时消除了手动特征工程的需要。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
