首页    期刊浏览 2024年11月24日 星期日
登录注册

文章基本信息

  • 标题:On the Hardness of Robust Classification
  • 本地全文:下载
  • 作者:Pascale Gourdeau ; Varun Kanade ; Marta Kwiatkowska
  • 期刊名称:Electronic Colloquium on Computational Complexity
  • 印刷版ISSN:1433-8092
  • 出版年度:2019
  • 卷号:2019
  • 页码:1-19
  • 出版社:Universität Trier, Lehrstuhl für Theoretische Computer-Forschung
  • 摘要:

    It is becoming increasingly important to understand the vulnerability of machine learning models to adversarial attacks. In this paper we study the feasibility of robust learning from the perspective of computational learning theory, considering both sample and computational complexity. In particular, our definition of robust learnability requires polynomial sample complexity. We start with two negative results. We show that no non-trivial concept class can be robustly learned in the distribution-free setting against an adversary who can perturb just a single input bit. We show moreover that the class of monotone conjunctions cannot be robustly learned under the uniform distribution against an adversary who can perturb ( log n ) input bits. However if the adversary is restricted to perturbing O ( log n ) bits, then the class of monotone conjunctions can be robustly learned with respect to a general class of distributions (that includes the uniform distribution). Finally, we provide a simple proof of the computational hardness of robust learning on the boolean hypercube. Unlike previous results of this nature, our result does not rely on another computational model (e.g. the statistical query model) nor on any hardness assumption other than the existence of a hard learning problem in the PAC framework.

  • 关键词:Adversarial Robustness ; Hardness of Learning ; PAC learning
国家哲学社会科学文献中心版权所有