Minimal Modifications of Deep Neural Networks using Verification
Ben Goldberger, Guy Katz, Yossi Adi, Joseph Keshet
Abstract
Deep neural networks (DNNs) are revolutionizing the way complex systems are de- signed, developed and maintained. As part of the life cycle of DNN-based systems, there is often a need to modify a DNN in subtle ways that affect certain aspects of its behav- ior, while leaving other aspects of its behavior unchanged (e.g., if a bug is discovered and needs to be fixed, without altering other functionality). Unfortunately, retraining a DNN is often difficult and expensive, and may produce a new DNN that is quite different from the original. We leverage recent advances in DNN verification and propose a technique for modifying a DNN according to certain requirements, in a way that is provably minimal, does not require any retraining, and is thus less likely to affect other aspects of the DNN’s behavior. Using a proof-of-concept implementation, we demonstrate the usefulness and potential of our approach in addressing two real-world needs: (i) measuring the resilience of DNN watermarking schemes; and (ii) bug repair in already-trained DNNs.