Adversarial patch-based attacks aim to fool a neural network with an intentionally generated noise, which is concentrated in a particular region of an input image. In this work, we perform an in-depth analysis of different patch generation parameters, including initialization, patch size, and especially positioning a patch in an image during training. We focus on the object vanishing attack and run experiments with YOLOv3 as a model under attack in a white-box setting and use images from the COCO dataset. Our experiments have shown, that inserting a patch inside a window of increasing size during training leads to a significant increase in attack strength compared to a fixed position. The best results were obtained when a patch was positioned randomly during training, while patch position additionally varied within a batch.
@article{arxiv.2209.13353,
title = {Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection},
author = {Svetlana Pavlitskaya and Jonas Hendl and Sebastian Kleim and Leopold Müller and Fabian Wylczoch and J. Marius Zöllner},
journal= {arXiv preprint arXiv:2209.13353},
year = {2022}
}