Attention Masks Help Adversarial Attacks to Bypass Safety Detectors

TL;DR

This paper introduces an adaptive attention mask framework that enhances the stealth and efficiency of PGD adversarial attacks against classifiers protected by explainability-based detectors, outperforming existing methods.

Contribution

It proposes a novel attention mask generation method using mutation XAI mixture and multitask self-supervised X-UNet to improve adversarial attack stealth and explainability.

Findings

Outperforms benchmark PGD, Sparsefool, and SINIFGSM in stealth and efficiency

Effective in fooling SOTA explainability-based defense classifiers

Demonstrates success on MNIST and CIFAR-10 datasets

Abstract

Despite recent research advancements in adversarial attack methods, current approaches against XAI monitors are still discoverable and slower. In this paper, we present an adaptive framework for attention mask generation to enable stealthy, explainable and efficient PGD image classification adversarial attack under XAI monitors. Specifically, we utilize mutation XAI mixture and multitask self-supervised X-UNet for attention mask generation to guide PGD attack. Experiments on MNIST (MLP), CIFAR-10 (AlexNet) have shown that our system can outperform benchmark PGD, Sparsefool and SOTA SINIFGSM in balancing among stealth, efficiency and explainability which is crucial for effectively fooling SOTA defense protected classifiers.