# Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection

Source: [Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e944>)

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

Data updated: 2025-10-26T00:52:04.916Z

Authors: Svetlana Pavlitskaya, Jonas Hendl, Sebastian Kleim, Leopold M\\"uller, Fabian Wylczoch, J. Marius Z\\"ollner

Published: 2022-09-27T12:59:19.000Z

## Abstract

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.

## 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/2209.13353>)

[PDF](<https://arxiv.org/pdf/2209.13353.pdf>)