PrivacyGuard可检测机器学习模型的隐私漏洞，支持多种攻击测试。
PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning
- 集成多种隐私攻击方法，可灵活配置分析场景
- 支持对模型进行实证差分隐私评估，量化隐私风险
- 模块化设计适合研究人员快速扩展新攻击与度量
机器学习模型在敏感领域的广泛应用催生了对可靠、实用隐私评估工具的需求。PrivacyGuard 是一个全面的实证差分隐私（DP）分析工具，通过前沿的推理攻击和先进的隐私度量技术，评估机器学习模型的隐私风险。该工具实现了多样化的隐私攻击，包括成员推理、数据提取和重构攻击，支持开箱即用及高度可配置的隐私分析。其模块化架构可无缝集成新攻击方法与隐私度量，便于快速适应新兴研究进展。项目开源地址：https://github.com/facebookresearch/PrivacyGuard。
原文摘要 · Abstract (English)
The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis, designed to evaluate privacy risks in ML models through state-of-the-art inference attacks and advanced privacy measurement techniques. To this end, PrivacyGuard implements a diverse suite of privacy attack -- including membership inference , extraction, and reconstruction attacks -- enabling both off-the-shelf and highly configurable privacy analyses. Its modular architecture allows for the seamless integration of new attacks, and privacy metrics, supporting rapid adaptation to emerging research advances. We make PrivacyGuard available at https://github.com/facebookresearch/PrivacyGuard.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。