A Theoretical Foundation and Practical Platform for Adversarial Machine Learning

对抗性机器学习的理论基础和实践平台

• 批准号: 543522-2019
• 负责人: Yu, Yaoliang
• 金额: $ 6.08万
• 依托单位: University of Waterloo
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=720728
• 关键词: Theoretical; Foundation; Practical; Platform; Adversarial

The recent impressive success of machine learning models has made them a promising candidate solution for virtually every application that requires extensive data analysis. With such bright promise comes the great scrutiny: these models are surprisingly non-robust against adversarial attacks. Many empirical studies have been performed, sometimes with seemingly contradicting conclusions. In this project, we aim to build a common theoretical foundation and a practical platform for performing research in adversarial machine learning. We provide an axiomatic approach to rigorously define, compute, and optimize robustness, along with other more conventional metrics, and we develop a platform to allow users to experiment with different notions of robustness and with different trade-offs among accuracy, robustness and efficiency. Our work will greatly clarify and streamline existing empirical work in a much needed unified and rigorous framework.

机器学习模型最近取得的令人印象深刻的成功使其成为几乎所有需要广泛数据分析的应用程序的有前途的候选解决方案。有了这样的光明前景，就有了更大的审查：这些模型对对抗性攻击的鲁棒性令人惊讶。已经进行了许多实证研究，有时得出的结论似乎相互矛盾。在这个项目中，我们的目标是建立一个共同的理论基础和实践平台，用于对抗机器学习的研究。我们提供了一个公理化的方法来严格定义，计算和优化的鲁棒性，沿着与其他更传统的指标，我们开发了一个平台，让用户实验不同的概念的鲁棒性和不同的权衡之间的准确性，鲁棒性和效率。我们的工作将在一个急需的统一和严格的框架内大大澄清和简化现有的经验工作。