Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection
This addresses security vulnerabilities in critical applications like surveillance and autonomous driving, though it is incremental as it focuses on quantifying known attack impacts.
The paper investigates how electromagnetic signal injection attacks affect object detection models by manipulating images through hardware interference, leading to incorrect detection results, and quantifies the impacts on state-of-the-art models while analyzing the underlying causes.
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 research work that comprehensively quantifies and analyzes the impacts of such attacks on state-of-the-art object detection models in practice. It also sheds light on the underlying reasons for the incorrect detection outcomes.