Saved in:
Bibliographic Details
Main Authors: Bayer, Jens, Becker, Stefan, Münch, David, Arens, Michael, Beyerer, Jürgen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.04991
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912810186833920
author Bayer, Jens
Becker, Stefan
Münch, David
Arens, Michael
Beyerer, Jürgen
author_facet Bayer, Jens
Becker, Stefan
Münch, David
Arens, Michael
Beyerer, Jürgen
contents Higher-order adversarial attacks can directly be considered the result of a cat-and-mouse game -- an elaborate action involving constant pursuit, near captures, and repeated escapes. This idiom describes the enduring circular training of adversarial attack patterns and adversarial training the best. The following work investigates the impact of higher-order adversarial attacks on object detectors by successively training attack patterns and hardening object detectors with adversarial training. The YOLOv10 object detector is chosen as a representative, and adversarial patches are used in an evasion attack manner. Our results indicate that higher-order adversarial patches are not only affecting the object detector directly trained on but rather provide a stronger generalization capacity compared to lower-order adversarial patches. Moreover, the results highlight that solely adversarial training is not sufficient to harden an object detector efficiently against this kind of adversarial attack. Code: https://github.com/JensBayer/HigherOrder
format Preprint
id arxiv_https___arxiv_org_abs_2601_04991
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Higher-Order Adversarial Patches for Real-Time Object Detectors
Bayer, Jens
Becker, Stefan
Münch, David
Arens, Michael
Beyerer, Jürgen
Computer Vision and Pattern Recognition
Higher-order adversarial attacks can directly be considered the result of a cat-and-mouse game -- an elaborate action involving constant pursuit, near captures, and repeated escapes. This idiom describes the enduring circular training of adversarial attack patterns and adversarial training the best. The following work investigates the impact of higher-order adversarial attacks on object detectors by successively training attack patterns and hardening object detectors with adversarial training. The YOLOv10 object detector is chosen as a representative, and adversarial patches are used in an evasion attack manner. Our results indicate that higher-order adversarial patches are not only affecting the object detector directly trained on but rather provide a stronger generalization capacity compared to lower-order adversarial patches. Moreover, the results highlight that solely adversarial training is not sufficient to harden an object detector efficiently against this kind of adversarial attack. Code: https://github.com/JensBayer/HigherOrder
title Higher-Order Adversarial Patches for Real-Time Object Detectors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.04991