EVOLVING INSIDER THREAT DETECTION STREAM MINING PERSPECTIVE
Authors:
- 24 October 2013
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 22 (05)
Abstract
Evidence of malicious insider activity is often buried within large data streams, such as system logs accumulated over months or years. Ensemble-based stream mining leverages multiple classification models to achieve highly accurate anomaly detection in such streams, even when the stream is unbounded, evolving, and unlabeled. This makes the approach effective for identifying insider threats who attempt to conceal their activities by varying their behaviors over time. This paper applies ensemble-based stream mining, supervised and unsupervised learning, and graph-based anomaly detection to the problem of insider threat detection. It demonstrates that the ensemble-based approach is significantly more effective than traditional single-model methods, supervised learning outperforms unsupervised learning, and increasing the cost of false negatives correlates to higher accuracy. Future work will consider a wider range of tunable parameters in an effort to further reduce false positives, include a more sophisticated polling algorithm for weighting better models, and implement parallelization to lower runtimes to more rapidly detect emerging insider threats.Keywords
This publication has 8 references indexed in Scilit:
- Insider Threat Detection Using a Graph-Based ApproachJournal of Applied Security Research, 2010
- Classification and Novel Class Detection in Concept-Drifting Data Streams under Time ConstraintsIEEE Transactions on Knowledge and Data Engineering, 2010
- A Survey of Insider Attack Detection Research2008
- Masquerade Detection Augmented With Error AnalysisIEEE Transactions on Reliability, 2004
- A framework for understanding and predicting insider attacksComputers & Security, 2002
- Graph-based data miningIEEE Intelligent Systems and their Applications, 2000
- Fast spinning into oblivion? Recent developments in money-laundering policies and offshore finance centresThird World Quarterly, 1999
- Intrusion detection using sequences of system callsJournal of Computer Security, 1998