Date of Award

3-14-2014

Document Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Department of Electrical and Computer Engineering

First Advisor

Kenneth M. Hopkinson, PhD.

Abstract

In the cyber domain, network defenders have traditionally been placed in a reactionary role. Before a defender can act they must wait for an attack to occur and identify the attack. This places the defender at a disadvantage in a cyber attack situation and it is certainly desirable that the defender out maneuver the attacker before the network has been compromised. The goal of this research is to determine the value of employing a recommender system as an attack predictor, and determine the best configuration of a recommender system for the cyber defense domain. The most important contribution of this research effort is the use of recommender systems to generate an ordered list of cyber defense actions.

AFIT Designator

AFIT-ENG-14-M-49

DTIC Accession Number

ADA600322

Share

COinS