TR2022-141

Improving Adversarial Robustness by Learning Shared Information


    •  Yu, X., Smedemark-Margulies, N., Aeron, S., Koike-Akino, T., Moulin, P., Brand, M.E., Parsons, K., Wang, Y., "Improving Adversarial Robustness by Learning Shared Information", Pattern Recognition, November 2022.
      BibTeX TR2022-141 PDF
      • @article{Yu2022nov,
      • author = {Yu, Xi and Smedemark-Margulies, Niklas and Aeron, Shuchin and Koike-Akino, Toshiaki and Moulin, Pierre and Brand, Matthew E. and Parsons, Kieran and Wang, Ye},
      • title = {Improving Adversarial Robustness by Learning Shared Information},
      • journal = {Pattern Recognition},
      • year = 2022,
      • month = nov,
      • url = {https://www.merl.com/publications/TR2022-141}
      • }
  • MERL Contacts:
  • Research Areas:

    Artificial Intelligence, Machine Learning, Signal Processing

Abstract:

We consider the problem of improving the adversarial robustness of neural networks while retaining natural accuracy. Motivated by the multi-view information bottleneck formalism, we seek to learn a representation that captures the shared information between clean samples and their corresponding adversarial samples while discarding these samples’ view-specific information. We show that this approach leads to a novel multi-objective loss function, and we provide mathematical motivation for its components towards improving the robust vs. natural accuracy tradeoff. We demonstrate enhanced tradeoff compared to current state-of-the- art methods with extensive evaluation on various benchmark image datasets and architectures. Ablation studies indicate that learning shared representations is key to improving performance.