ReluDiff: Differential Verification of Deep Neural Networks
Abstract
As deep neural networks are increasingly being deployed in practice, their efficiency has become an important issue. While there are compression techniques for reducing the network's size, energy consumption and computational requirement, they only demonstrate empirically that there is no loss of accuracy, but lack formal guarantees of the compressed network, e.g., in the presence of adversarial examples. Existing verification techniques such as Reluplex, ReluVal, and DeepPoly provide formal guarantees, but they are designed for analyzing a single network instead of the relationship between two networks. To fill the gap, we develop a new method for differential verification of two closely related networks. Our method consists of a fast but approximate forward interval analysis pass followed by a backward pass that iteratively refines the approximation until the desired property is verified. We have two main innovations. During the forward pass, we exploit structural and behavioral similarities of the two networks to more accurately bound the difference between the output neurons of the two networks. Then in the backward pass, we leverage the gradient differences to more accurately compute the most beneficial refinement. Our experiments show that, compared to state-of-the-art verification tools, our method can achieve orders-of-magnitude speedup and prove many more properties than existing tools.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2020
- DOI:
- 10.48550/arXiv.2001.03662
- arXiv:
- arXiv:2001.03662
- Bibcode:
- 2020arXiv200103662P
- Keywords:
-
- Computer Science - Machine Learning;
- Computer Science - Logic in Computer Science;
- Computer Science - Software Engineering;
- Statistics - Machine Learning
- E-Print:
- Extended version of ICSE 2020 paper. This version includes an appendix with proofs for some of the content in section 4.3