Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection
Youqian Zhang, Chunxi Yang, Eugene Y. Fu, Qinhong Jiang, Chen Yan,, Sze-Yiu Chau, Grace Ngai, Hong-Va Leong, Xiapu Luo, Wenyuan Xu

TL;DR
This paper investigates how electromagnetic signal injection attacks can disrupt object detection systems by causing noisy or incomplete images, leading to incorrect detections in critical applications like security and autonomous driving.
Contribution
It provides a comprehensive analysis of the effects of electromagnetic interference attacks on modern object detection models, highlighting underlying causes of detection failures.
Findings
Electromagnetic attacks can significantly degrade detection accuracy.
Attacks cause noisy or incomplete images, leading to false detections.
Analysis reveals key vulnerabilities in object detection systems.
Abstract
Object detection can localize and identify objects in images, and it is extensively employed in critical multimedia applications such as security surveillance and autonomous driving. Despite the success of existing object detection models, they are often evaluated in ideal scenarios where captured images guarantee the accurate and complete representation of the detecting scenes. However, images captured by image sensors may be affected by different factors in real applications, including cyber-physical attacks. In particular, attackers can exploit hardware properties within the systems to inject electromagnetic interference so as to manipulate the images. Such attacks can cause noisy or incomplete information about the captured scene, leading to incorrect detection results, potentially granting attackers malicious control over critical functions of the systems. This paper presents a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
