Skip to main content
CausalAdv: Adversarial Robustness through the Lens of Causality
  • Yonggang Zhang, University of Science and Technology of China, China & Hong Kong Baptist University, Hong Kong
  • Mingming Gong, The University of Melbourne, Australia
  • Tongliang Liu, The University of Sydney, Australia
  • Gang Niu, RIKEN Center for Advanced Intelligence Project, Japan
  • Xinmei Tian, University of Science and Technology of China, China
  • Bo Han, Hong Kong Baptist University, Hong Kong
  • Bernhard Schölkopf, Max Planck Institute for Intelligent Systems, Germany
  • Kun Zhang, Carnegie Mellon University & Mohamed bin Zayed University of Artificial Intelligence
Document Type

The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning. As causal reasoning has an instinct for modeling distribution change, it is essential to incorporate causality into analyzing this specific type of distribution change induced by adversarial attacks. However, causal formulations of the intuition of adversarial attacks and the development of robust DNNs are still lacking in the literature. To bridge this gap, we construct a causal graph to model the generation process of adversarial examples and define the adversarial distribution to formalize the intuition of adversarial attacks. From the causal perspective, we study the distinction between the natural and adversarial distribution and conclude that the origin of adversarial vulnerability is the focus of models on spurious correlations. Inspired by the causal understanding, we propose the Causal-inspired Adversarial distribution alignment method, CausalAdv, to eliminate the difference between natural and adversarial distributions by considering spurious correlations. Extensive experiments demonstrate the efficacy of the proposed method. Our work is the first attempt towards using causality to understand and mitigate the adversarial vulnerability. Copyright © 2021, The Authors. All rights reserved.

Publication Date
  • Alignment methods,
  • Causal graph,
  • Causal reasoning,
  • Generation process,
  • Modeling distributions,
  • Through the lens,
  • Deep neural networks,
  • Machine Learning (cs.LG)

Preprints available on arXiv

Citation Information
Y. Zhang, et al, "CausalAdv: Adversarial Robustness through the Lens of Causality", 2021, arXiv:2106.06196