Insider threats are the cyber attacks from within the trusted entities of anorganization . Lack of real-world data and issue of data imbalance leave insiderthreat analysis an understudied research area . We propose an approach that combinesgenerative model with supervised learning to perform multi-class classification using deep learning . The method is compared with other existing methods against different parameters and performance metrics. The comprehensive experiments performed on the benchmark datasetdemonstrates the effectiveness of introducing GAN derived synthetic data and the capability of multi class anomaly detection in insider activity analysis. The method was compared with . other existing . methods against . different .parameters and performance . metrics .

Author(s) : R G Gayathri, Atul Sajjanhar, Yong Xiang, Xingjun Ma

Links : PDF - Abstract

Code :

Keywords : multi - data - insider - class - detection -

Leave a Reply

Your email address will not be published. Required fields are marked *