No abstract

No abstract

No abstract

State-of-the-art deep neural networks are sensitive to small input perturbations. Since the discovery of this intriguing vulnerability, many defence methods have been proposed that attempt to improve robustness to adversarial noise. Fast and accurate attacks are required to compare various defence methods. However, evaluating adversarial robustness has proven to be extremely challenging. Existing norm minimisation adversarial attacks require thousands of iterations (e.g. Carlini & Wagner attack), are limited to the specific norms (e.g. Fast Adaptive Boundary), or produce sub-optimal results (e.g. Brendel & Bethge attack). On the other hand, PGD attack, which is fast, general and accurate, ignores the norm minimisation penalty and solves a simpler perturbation-constrained problem. In this work, we introduce a fast, general and accurate adversarial attack that optimises the original non-convex constrained minimisation problem. We interpret optimising the Lagrangian of the adversarial attack optimisation problem as a two-player game: the first player minimises the Lagrangian wrt the adversarial noise; the second player maximises the Lagrangian wrt the regularisation penalty. Our attack algorithm simultaneously optimises primal and dual variables to find the minimal adversarial perturbation. In addition, for non-smooth lp-norm minimisation, such as l∞-, l1-, and l0-norms, we introduce primal-dual proximal gradient descent attack. We show in the experiments that our attack outperforms current state-of-the-art l∞-, l2-, l1-, and l0-attacks on MNIST, CIFAR-10 and Restricted ImageNet datasets against unregularised and adversarially trained models.

This thesis contains material from papers accepted at conferences in which I am listed as an author. Chapter 3 is published as Alexander Matyasko, Lap Pui Chau. Margin maximization for robust classification using deep learning. In International Joint Conference on Neural Networks (IJCNN). 300-307 (2017).