# Generative Dynamic Patch Attack

Source: [Generative Dynamic Patch Attack](<https://www.sota2.com/research/paper/68fa6b441e209131cea2d1bc>)

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

Data updated: 2025-10-25T23:44:09.187Z

Authors: Xiang Li, Shihao Ji

Published: 2021-11-08T04:15:34.000Z

## Abstract

Adversarial patch attack is a family of attack algorithms that perturb a part of image to fool a deep neural network model. Existing patch attacks mostly consider injecting adversarial patches at input-agnostic locations: either a predefined location or a random location. This attack setup may be sufficient for attack but has considerable limitations when using it for adversarial training. Thus, robust models trained with existing patch attacks cannot effectively defend other adversarial attacks. In this paper, we first propose an end-to-end patch attack algorithm, Generative Dynamic Patch Attack (GDPA), which generates both patch pattern and patch location adversarially for each input image. We show that GDPA is a generic attack framework that can produce dynamic/static and visible/invisible patches with a few configuration changes. Secondly, GDPA can be readily integrated for adversarial training to improve model robustness to various adversarial attacks. Extensive experiments on VGGFace, Traffic Sign and ImageNet show that GDPA achieves higher attack success rates than state-of-the-art patch attacks, while adversarially trained model with GDPA demonstrates superior robustness to adversarial patch attacks than competing methods. Our source code can be found at https://github.com/lxuniverse/gdpa.

## 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/2111.04266>)

[PDF](<https://arxiv.org/pdf/2111.04266.pdf>)
