Paper
13 November 2024 Network transferability of adversarial patches in real-time object detection
Author Affiliations +
Abstract
Adversarial patches in computer vision can be used, to fool deep neural networks and manipulate their decisionmaking process. One of the most prominent examples of adversarial patches are evasion attacks for object detectors. By covering parts of objects of interest, these patches suppress the detections and thus make the target object “invisible” to the object detector. Since these patches are usually optimized on a specific network with a specific train dataset, the transferability across multiple networks and datasets is not given. This paper addresses these issues and investigates the transferability across numerous object detector architectures. Our extensive evaluation across various models on two distinct datasets indicates that patches optimized with larger models provide better network transferability than patches that are optimized with smaller models.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jens Bayer, Stefan Becker, David Münch, and Michael Arens "Network transferability of adversarial patches in real-time object detection", Proc. SPIE 13206, Artificial Intelligence for Security and Defence Applications II, 132060X (13 November 2024); https://doi.org/10.1117/12.3031501
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Object detection

Network architectures

Back to Top