Intrusion/misuse detection is the top information assurance priority of both the national interagency INFOSEC Research Council
and the Office of the Assistant Secretary of Defense. Traditional IDSs are effective at detecting known attacks; however,
developing truly proactive defensive systems remains an open problem. This research investigates the feasibility of using
evolutionary search techniques, in the context of a computer immune system, to detect computer network intrusions, with particular
emphasis on developing techniques for catching new attacks. The system provided very low false-negative and false-positive
error rates during initial experimentation.
The material reported herein is based primarily on the first author’s thesis submitted in partial fulfillment of the requirements
for the Master of Science degree at the Air Force Institute of Technology, Wright-Patterson AFB, OH, March 2001. The views
expressed in this article are those of the authors and do not reflect the official policy or position of the United States
Air Force, Department of Defense, or the U.S. Government.