Improving adversarial robustness by learning shared information

Xi Yu, Niklas Smedemark-Margulies, Shuchin Aeron, Toshiaki Koike-Akino, Pierre Moulin, Matthew Brand, Kieran Parsons, Ye Wang

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish (US)
Article number109054
JournalPattern Recognition
Volume134
DOIs
StatePublished - Feb 2023
Externally publishedYes

Keywords

  • Adversarial robustness
  • Information bottleneck
  • Multi-view learning
  • Shared information

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Improving adversarial robustness by learning shared information'. Together they form a unique fingerprint.

Cite this