A categorically reweighted feature extraction method for anomaly detection

Ruyao Cui, Lei Sun, Jie Yang, Bo Liu, Yuan Fan

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Anomaly detection is an important research problem in diverse computer security areas. Reliability of normal and abnormal samples is generally different in practice. We propose a scheme with a categorical re-weighting parameter to utilize this categorical reliability difference for feature extraction in anomaly detection. It is shown that this re-weighting parameter provides a method to tune the decision hyperplane between normal and abnormal classes. Based on two existing feature extraction algorithms, two new feature extraction algorithms using the proposed scheme are designed, which generalize the existing methods. Experiments show that the proposed methods outperform the previous state-of-arts in terms of both classification accuracy and robustness on synthetic and real-world data sets.

源语言英语
主期刊名Proceedings - 2018 IEEE 3rd International Conference on Data Science in Cyberspace, DSC 2018
出版商Institute of Electrical and Electronics Engineers Inc.
697-704
页数8
ISBN(电子版)9781538642108
DOI
出版状态已出版 - 16 7月 2018
活动3rd IEEE International Conference on Data Science in Cyberspace, DSC 2018 - Guangzhou, Guangdong, 中国
期限: 18 6月 201821 6月 2018

出版系列

姓名Proceedings - 2018 IEEE 3rd International Conference on Data Science in Cyberspace, DSC 2018

会议

会议3rd IEEE International Conference on Data Science in Cyberspace, DSC 2018
国家/地区中国
Guangzhou, Guangdong
时期18/06/1821/06/18

指纹

探究 'A categorically reweighted feature extraction method for anomaly detection' 的科研主题。它们共同构成独一无二的指纹。

引用此