Reducing False Positive In Intrusion Detection using Genetic Algorithm
Author(s):
Dipika Narsingyani, Ompriya Kale
Keywords:
Genetic Algorithms, False Positive, Features Selection, Intrusion Detection
Abstract
Intrusion detection system (IDS) is one more arrow in the bow of Computer network Security. This can be part of the firewall of can be independently installed. The work of IDS is basically to worn the system against network activity that are not looking normal in the current setting. This can be done by two ways. One is to maintain database of security threat patterns, but as attacks are increasing day by day, it would be very difficult to maintain complete database of all attack types. Second is to employ some machine learning technique to classify network intrusion using their characteristic and deviation from normal traffic. Second approach is called anomaly detection. The major problem with anomaly based intrusion detection is the false alarm. False alarm is a indication of threat by security system, for normal network activity. False alarm badly affects system performance by misdirecting and consuming resources in analyzing normal connection as threats. Genetic algorithm is one the most promising evolutionary algorithm for optimization for one or more than one objective at a same time. The research in this thesis is devoted to optimize false alarm on DoS attack by employing genetic algorithm.
Article Details
Unique Paper ID: 142392
Publication Volume & Issue: Volume 2, Issue 1
Page(s): 104 - 107
Article Preview & Download
Share This Article
Conference Alert
NCSST-2023
AICTE Sponsored National Conference on Smart Systems and Technologies
Last Date: 25th November 2023
SWEC- Management
LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT