Overload: Latency Attacks on Object Detection for Edge Devices

arXiv:2304.05370v3 Announce Type: replace
Abstract: Nowadays, the deployment of deep learning-based applications is an essential task owing to the increasing demands on intelligent services. In this paper, we investigate latency attacks on deep learning applications. Unlike common adversarial attacks for misclassification, the goal of latency attacks is to increase the inference time, which may stop applications from responding to the requests within a reasonable time. This kind of attack is ubiquitous for various applications, and we use object detection to …

abstract adversarial adversarial attacks applications arxiv attacks cs.cv deep learning deployment detection devices edge edge devices inference intelligent latency object overload paper services type