Weakly Supervised Anomaly Detection via Knowledge-Data Alignment

no code implementations • 6 Feb 2024 • Haihong Zhao, Chenyi Zi, Yang Liu, Chen Zhang, Yan Zhou, Jia Li

In this paper, we introduce a novel framework Knowledge-Data Alignment (KDAlign) to integrate rule knowledge, typically summarized by human experts, to supplement the limited labeled data.

Malware Detection Supervised Anomaly Detection +1