TAPS: Connecting Certified and Adversarial Training

Code

• github.com/eth-sri/taps
  OfficialIn paperpytorch★ 3
• github.com/eth-sri/ibp-propagation-tightness
  pytorch★ 2

Abstract

Training certifiably robust neural networks remains a notoriously hard problem. On one side, adversarial training optimizes under-approximations of the worst-case loss, which leads to insufficient regularization for certification, while on the other, sound certified training methods optimize loose over-approximations, leading to over-regularization and poor (standard) accuracy. In this work we propose TAPS, an (unsound) certified training method that combines IBP and PGD training to yield precise, although not necessarily sound, worst-case loss approximations, reducing over-regularization and increasing certified and standard accuracies. Empirically, TAPS achieves a new state-of-the-art in many settings, e.g., reaching a certified accuracy of 22\% on TinyImageNet for _-perturbations with radius =1/255. We make our implementation and networks public at https://github.com/eth-sri/taps.

Reproductions