Adversarial example generation with AdaBelief Optimizer and Crop Invariance

TL;DR

This paper introduces new gradient-based attack methods, ABI-FGM and CIM, that significantly improve the transferability and success rates of adversarial examples against robust models, including adversarially trained networks, on ImageNet.

Contribution

The paper proposes novel attack algorithms that enhance transferability of adversarial examples, outperforming existing methods against defense models.

Findings

Higher success rates on adversarially trained networks.

Effective against advanced defense models.

Improved transferability of adversarial examples.

Abstract

Deep neural networks are vulnerable to adversarial examples, which are crafted by applying small, human-imperceptible perturbations on the original images, so as to mislead deep neural networks to output inaccurate predictions. Adversarial attacks can thus be an important method to evaluate and select robust models in safety-critical applications. However, under the challenging black-box setting, most existing adversarial attacks often achieve relatively low success rates on adversarially trained networks and advanced defense models. In this paper, we propose AdaBelief Iterative Fast Gradient Method (ABI-FGM) and Crop-Invariant attack Method (CIM) to improves the transferability of adversarial examples. ABI-FGM and CIM can be readily integrated to build a strong gradient-based attack to further boost the success rates of adversarial examples for black-box attacks. Moreover, our method can also be naturally combined with other gradient-based attack methods to build a more robust attack to generate more transferable adversarial examples against the defense models. Extensive experiments on the ImageNet dataset demonstrate the method's effectiveness. Whether on adversarially trained networks or advanced defense models, our method has higher success rates than state-of-the-art gradient-based attack methods.