OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks

TL;DR

This paper introduces OccRob, an efficient SMT-based method for formally verifying the occlusion robustness of deep neural networks, addressing a critical gap in safety-critical applications.

Contribution

It presents the first formal, SMT-based approach for occlusion robustness verification, including novel encoding techniques and acceleration methods for efficient analysis.

Findings

Effective verification of DNNs against occlusions demonstrated

Ability to generate counterexamples when DNNs lack robustness

Significant efficiency improvements over baseline methods

Abstract

Occlusion is a prevalent and easily realizable semantic perturbation to deep neural networks (DNNs). It can fool a DNN into misclassifying an input image by occluding some segments, possibly resulting in severe errors. Therefore, DNNs planted in safety-critical systems should be verified to be robust against occlusions prior to deployment. However, most existing robustness verification approaches for DNNs are focused on non-semantic perturbations and are not suited to the occlusion case. In this paper, we propose the first efficient, SMT-based approach for formally verifying the occlusion robustness of DNNs. We formulate the occlusion robustness verification problem and prove it is NP-complete. Then, we devise a novel approach for encoding occlusions as a part of neural networks and introduce two acceleration techniques so that the extended neural networks can be efficiently verified using off-the-shelf, SMT-based neural network verification tools. We implement our approach in a prototype called OccRob and extensively evaluate its performance on benchmark datasets with various occlusion variants. The experimental results demonstrate our approach's effectiveness and efficiency in verifying DNNs' robustness against various occlusions, and its ability to generate counterexamples when these DNNs are not robust.