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.

翻译：尽管对抗攻击方法的研究近期取得了进展，但当前针对XAI监测器的攻击方法仍可被检测且速度较慢。本文提出一种自适应注意力掩码生成框架，用于在XAI监测下实现隐蔽、可解释且高效的PGD图像分类对抗攻击。具体而言，我们利用变异XAI混合与多任务自监督X-UNet生成注意力掩码来指导PGD攻击。在MNIST（MLP）和CIFAR-10（AlexNet）上的实验表明，我们的系统在隐蔽性、效率与可解释性之间的平衡上超越了基准PGD、Sparsefool及当前最优的SINIFGSM方法，这对于有效欺骗受先进防御保护的分类器至关重要。