Backdoor Attack against One-Class Sequential Anomaly Detection Models

arXiv:2402.10283v1 Announce Type: new
Abstract: Deep anomaly detection on sequential data has garnered significant attention due to the wide application scenarios. However, deep learning-based models face a critical security threat - their vulnerability to backdoor attacks. In this paper, we explore compromising deep sequential anomaly detection models by proposing a novel backdoor attack strategy. The attack approach comprises two primary steps, trigger generation and backdoor injection. Trigger generation is to derive imperceptible triggers by crafting perturbed samples from the benign …

abstract anomaly anomaly detection application arxiv attacks attention backdoor class cs.ai cs.cr cs.it cs.lg data deep learning detection explore face math.it novel paper security threat type vulnerability