Universal Adversarial Robustness of Texture and Shape-Biased Models

Abstract

Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise. In this paper we analyze the adversarial robustness of texture and shape-biased models to Universal Adversarial Perturbations (UAPs). We use UAPs to evaluate the robustness of DNN models with varying degrees of shape-based training. We find that shape-biased models do not markedly improve adversarial robustness, and we show that ensembles of texture and shape-biased models can improve universal adversarial robustness while maintaining strong performance.

In Proceedings of the 28th IEEE International Conference on Image Processing (ICIP 2021), code available at: https://github.com/kenny-co/sgd-uap-torch

References in corpus (3)

• Evasion Attacks against Machine Learning at Test Time
• Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks
• Jacobian Regularization for Mitigating Universal Adversarial Perturbations