Higher-Order Adversarial Patches for Real-Time Object Detectors

TL;DR

This paper explores higher-order adversarial patches against real-time object detectors, demonstrating their superior generalization and the limitations of adversarial training in defending against such attacks.

Contribution

It introduces higher-order adversarial patches for object detectors and shows their effectiveness and the challenges in defending against them through adversarial training.

Findings

Higher-order patches improve attack transferability

Adversarial training alone is insufficient for robustness

Higher-order patches generalize better than lower-order ones

Abstract

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