Transferable Sparse Adversarial Attack

Abstract

Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the ${\ell }_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a high attack success rate, prior sparse attack methods achieve a low transferability under the black-box protocol due to overfitting the target model. Therefore, we introduce a generator architecture to alleviate the overfitting issue and thus efficiently craft transferable sparse adversarial examples. Specifically, the generator decouples the sparse perturbation into amplitude and position components. We carefully design a random quantization operator to optimize these two components jointly in an end-to-end way. The experiment shows that our method has improved the transferability by a large margin under a similar sparsity setting compared with state-of-the-art methods. Moreover, our method achieves superior inference speed, 700$\times$ faster than other optimization-based methods. The code is available at https://github.com/shaguopohuaizhe/TSAA.

References in corpus (7)

• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Generating Adversarial Examples with Adversarial Networks
• Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• Constructing Unrestricted Adversarial Examples with Generative Models
• An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networks
• GeoDA: a geometric framework for black-box adversarial attacks