# Attention Masks Help Adversarial Attacks to Bypass Safety Detectors

arXiv: https://arxiv.org/abs/2411.04772 · HTML: https://mlsanity.com/paper/2411.04772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 6 of 6)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures](https://mlsanity.com/paper/1909.03418/) (2019)
- [Outside the Box: Abstraction-Based Monitoring of Neural Networks](https://mlsanity.com/paper/1911.09032/) (2019)
- [Benchmarking Safety Monitors for Image Classifiers with Machine Learning](https://mlsanity.com/paper/2110.01232/) (2021)
- [Backdooring Explainable Machine Learning](https://mlsanity.com/paper/2204.09498/) (2022)
- [Can Perceptual Guidance Lead to Semantically Explainable Adversarial Perturbations?](https://mlsanity.com/paper/2106.12731/) (2021)

## Abstract (arXiv)

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.