Input Validation for Neural Networks via Runtime Local Robustness Verification
This addresses security vulnerabilities in neural networks for applications like image recognition, but it is incremental as it builds on existing verification techniques.
The paper tackles the problem of protecting neural networks from adversarial examples by proposing input validation via runtime local robustness verification, showing that it can improve network accuracies.
Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs are much larger than that of misclassified inputs which include adversarial examples, especially those from strong adversarial attacks. Another observation is that the robustness radii of correctly classified inputs often follow a normal distribution. Based on these two observations, we propose to validate inputs for neural networks via runtime local robustness verification. Experiments show that our approach can protect neural networks from adversarial examples and improve their accuracies.