# Attention Masks Help Adversarial Attacks to Bypass Safety Detectors

Source: [Attention Masks Help Adversarial Attacks to Bypass Safety Detectors](<https://www.sota2.com/research/paper/68fa759f1e209131cea69058>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-14T19:44:36.671Z

Authors: Yunfan Shi

Published: 2024-11-07T15:13:50.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.04772>)

[PDF](<https://arxiv.org/pdf/2411.04772.pdf>)