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

by   Xingwu Guo, et al.

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.


page 4

page 14


Accelerating Robustness Verification of Deep Neural Networks Guided by Target Labels

Deep Neural Networks (DNNs) have become key components of many safety-cr...

A DPLL(T) Framework for Verifying Deep Neural Networks

Deep Neural Networks (DNNs) have emerged as an effective approach to tac...

Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification

Deep neural networks (DNNs) have been shown lack of robustness for the v...

Verifying Robustness of Gradient Boosted Models

Gradient boosted models are a fundamental machine learning technique. Ro...

Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations

It is known that deep neural networks (DNNs) classify an input image by ...

Efficient Cloth Simulation using Miniature Cloth and Upscaling Deep Neural Networks

Cloth simulation requires a fast and stable method for interactively and...

An SMT-Based Approach for Verifying Binarized Neural Networks

Deep learning has emerged as an effective approach for creating modern s...

Please sign up or login with your details

Forgot password? Click here to reset