Feature fusion for unified adversarial attack detection for object detection
conference paper
Integration of AI-based object detection has accelerated in a variety of defense applications, such as intelligence surveillance reconnaissance (ISR) and autonomous systems. However, the AI-based methods that enable these capabilities are inherently vulnerable to adversarial attacks, which are physical or digital input perturbations designed to mislead AI systems and induce incorrect or unpredictable behaviour. For object detection, such attacks can suppress or alter detections of critical targets, thereby undermining situational awareness, compromising mission integrity, or even disabling automated defense responses. Detecting these attacks is essential to the security of AI-driven military systems. In this work, we propose a unified adversarial attack detection approach, capable of identifying two distinct types of adversarial attacks for object detection, currently underexplored in the literature. We build on an existing method that leverages both local and global spatial image features to detect localized patch-based attacks. We extend this approach by introducing a fusion mechanism between these features to enable detection of white-box global and black-box local image perturbation attacks. Both the attacks target the state-of-the-art YOLOv10m object detector, trained on both the MS COCO and the military Automatic Target Recognition (ATR) object detection datasets. We show that with our feature fusion approach an attack detection accuracy of 99% can be achieved for both attacks, comparable to detectors specialized for single type attacks. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.
Topics
TNO Identifier
1023331
ISSN
0277786X
Publisher
SPIE
Article nr.
136791H
Source title
3rd Artificial Intelligence for Security and Defence Applications, Madrid, 2025-09-16 through 2025-09-18
Pages
1-7
Files
To receive the publication files, please send an e-mail request to TNO Repository.