Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Atypical Behavior Identification in Large Scale Network Traffic

Conference ·

Cyber analysts are faced with the daunting challenge of identifying exploits and threats within potentially billions of daily records of network traffic. Enterprise-wide cyber traffic involves hundreds of millions of distinct IP addresses and results in data sets ranging from terabytes to petabytes of raw data. Creating behavioral models and identifying trends based on those models requires data intensive architectures and techniques that can scale as data volume increases. Analysts need scalable visualization methods that foster interactive exploration of data and enable identification of behavioral anomalies. Developers must carefully consider application design, storage, processing, and display to provide usability and interactivity with large-scale data. We present an application that highlights atypical behavior in enterprise network flow records. This is accomplished by utilizing data intensive architectures to store the data, aggregation techniques to optimize data access, statistical techniques to characterize behavior, and a visual analytic environment to render the behavioral trends, highlight atypical activity, and allow for exploration.

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC05-76RL01830
OSTI ID:
1042556
Report Number(s):
PNNL-SA-79591; 400904120
Country of Publication:
United States
Language:
English

Similar Records

Data Intensive Architecture for Scalable Cyber Analytics
Conference · Mon Nov 14 23:00:00 EST 2011 · OSTI ID:1038400

Data Intensive Architecture for Scalable Cyber Analytics
Conference · Sun Dec 18 23:00:00 EST 2011 · OSTI ID:1092699

Challenge Paper: Validation of Forensic Techniques for Criminal Prosecution
Conference · Tue Apr 10 00:00:00 EDT 2007 · OSTI ID:983450