Accession Number:

AD1082697

Title:

Large-Scale Network Inference: Detecting the Unknown and the Intermittent

Descriptive Note:

Technical Report,05 Sep 2017,04 Jun 2018

Corporate Author:

Cornell University Ithaca United States

Personal Author(s):

Report Date:

2018-09-04

Pagination or Media Count:

7.0

Abstract:

Accurate and timely detection of network anomalies or unusual activities, be it endogenous caused by internal malfunctioning components or exogenous caused by hostile attacks and intrusions, is crucial to the functionality and survivability of tactical military networks. The objective of this research is to develop general design methodologies for large-scale network inference for anomaly detection. We aim to establish fundamental limits on sample complexityin particular, the scaling behavior of sample complexity with respect to the problem size and the detection accuracyand develop efficient algorithms that achieve or approach the fundamental limits with scalable low-complexity implementations. Our emphasis is on low-complexity deterministic strategies with implementations scalable to large networks.

Subject Categories:

  • Computer Systems Management and Standards

Distribution Statement:

APPROVED FOR PUBLIC RELEASE