Robustness against Adversarial Attacks in Neural Networks using Incremental Dissipativity
This work addresses robustness for neural network users against adversarial attacks, but it is incremental as it builds on existing system-theoretic certificates.
The paper tackled the problem of adversarial attacks degrading neural network classification by proposing an incremental dissipativity-based robustness certificate, demonstrating improved performance on MNIST and CIFAR-10 datasets.
Adversarial examples can easily degrade the classification performance in neural networks. Empirical methods for promoting robustness to such examples have been proposed, but often lack both analytical insights and formal guarantees. Recently, some robustness certificates have appeared in the literature based on system theoretic notions. This work proposes an incremental dissipativity-based robustness certificate for neural networks in the form of a linear matrix inequality for each layer. We also propose an equivalent spectral norm bound for this certificate which is scalable to neural networks with multiple layers. We demonstrate the improved performance against adversarial attacks on a feed-forward neural network trained on MNIST and an Alexnet trained using CIFAR-10.