Chapter 19 described in detail our approach to insider threat detection for sequence data. In particular, both supervised and unsupervised learning techniques for streaming data were discussed. In this chapter, we will provide an overview of the testing methodology and the experimental results. We will present sequence dataset that we used for our experiments. Second, we present how we inject concept drift in the dataset. Finally, we present results showing the anomaly detection rate in the presence of concept drift1.
The organization of this chapter is as follows. The dataset used is discussed in Section 20.2. Concept-drift aspects are discussed in Section 20.3. Results are presented ...
Get Big Data Analytics with Applications in Insider Threat Detection now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
