Understanding Certified Training with Interval Bound Propagation

arXiv:2306.10426v2 Announce Type: replace
Abstract: As robustness verification methods are becoming more precise, training certifiably robust neural networks is becoming ever more relevant. To this end, certified training methods compute and then optimize an upper bound on the worst-case loss over a robustness specification. Curiously, training methods based on the imprecise interval bound propagation (IBP) consistently outperform those leveraging more precise bounding methods. Still, we lack an understanding of the mechanisms making IBP so successful.
In this work, we thoroughly …

abstract arxiv case compute cs.ai cs.lg interval loss networks neural networks propagation robust robustness training type understanding verification