Timezone: »
Poster
Stronger and Faster Wasserstein Adversarial Attacks
Kaiwen Wu · Allen Wang · Yaoliang Yu
Tue Jul 14 08:00 AM -- 08:45 AM & Tue Jul 14 07:00 PM -- 07:45 PM (PDT) @ Virtual #None
Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to ``small, imperceptible'' perturbations known as adversarial attacks. While the majority of existing attacks focuses on measuring perturbations under the $\ell_p$ metric, Wasserstein distance, which takes geometry in pixel space into account, has long known to be a better metric for measuring image quality and has recently risen as a compelling alternative to the $\ell_p$ metric in adversarial attacks. However, constructing an effective attack under the Wasserstein metric is computationally much more challenging and calls for better optimization algorithms. We address this gap in two ways: (a) we develop an exact yet efficient projection operator to enable a stronger projected gradient attack; (b) we show for the first time that Frank-Wolfe method equipped with a suitable linear minimization oracle works extremely fast under Wasserstein constraints. Our algorithms not only converge faster but also generate much stronger attacks. For instance, we decrease the accuracy of a residual network on CIFAR-10 to $3.4\%$ within a Wasserstein perturbation ball of radius $0.005$, in contrast to $65.5\%$ using the previous state-of-the-art attack based on approximate projection.
We show that applying our stronger attacks in adversarial training significantly improves the robustness of adversarially trained models.
Author Information
Kaiwen Wu (University of Waterloo)
Allen Wang (University of Waterloo)
Yaoliang Yu (University of Waterloo)
More from the Same Authors
-
2020 Poster: Tails of Lipschitz Triangular Flows »
Priyank Jaini · Ivan Kobyzev · Yaoliang Yu · Marcus Brubaker -
2020 Poster: Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space »
Yingyi Ma · Vignesh Ganapathiraman · Yaoliang Yu · Xinhua Zhang -
2019 Poster: Sum-of-Squares Polynomial Flow »
Priyank Jaini · Kira A. Selby · Yaoliang Yu -
2019 Oral: Sum-of-Squares Polynomial Flow »
Priyank Jaini · Kira A. Selby · Yaoliang Yu -
2019 Poster: Distributional Reinforcement Learning for Efficient Exploration »
Borislav Mavrin · Hengshuai Yao · Linglong Kong · Kaiwen Wu · Yaoliang Yu -
2019 Oral: Distributional Reinforcement Learning for Efficient Exploration »
Borislav Mavrin · Hengshuai Yao · Linglong Kong · Kaiwen Wu · Yaoliang Yu -
2018 Poster: Inductive Two-Layer Modeling with Parametric Bregman Transfer »
Vignesh Ganapathiraman · Zhan Shi · Xinhua Zhang · Yaoliang Yu -
2018 Oral: Inductive Two-Layer Modeling with Parametric Bregman Transfer »
Vignesh Ganapathiraman · Zhan Shi · Xinhua Zhang · Yaoliang Yu