JAX-Privacy简化差分隐私机器学习的部署，兼顾易用与高效。
JAX-Privacy: A library for differentially private machine learning
- 提供模块化隐私机制组件，支持梯度裁剪、噪声添加等关键操作。
- 整合近期研究进展，实现可验证的差分隐私保障。
- 适合需要定制化或快速上手的科研与工程人员。
JAX-Privacy 是一个旨在简化鲁棒且高效的差分隐私机器学习机制部署的库。遵循可用性、灵活性和效率的设计原则，该库既满足研究人员对深度定制的需求，也为希望即插即用的实践者提供便利。它提供了经过验证的模块化原语，覆盖机制设计中的所有关键环节，包括批量选择、梯度裁剪、噪声添加、隐私预算会计和审计，并整合了大量近期关于差分隐私机器学习的研究成果。
原文摘要 · Abstract (English)
JAX-Privacy is a library designed to simplify the deployment of robust and performant mechanisms for differentially private machine learning. Guided by design principles of usability, flexibility, and efficiency, JAX-Privacy serves both researchers requiring deep customization and practitioners who want a more out-of-the-box experience. The library provides verified, modular primitives for critical components for all aspects of the mechanism design including batch selection, gradient clipping, noise addition, accounting, and auditing, and brings together a large body of recent research on differentially private ML.
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。