Multi-agent artificial immune system for network intrusion detection and classification

Citation:
Aziz, A. S. A., S. E. - O. Hanafy, and A. E. Hassanien, "Multi-agent artificial immune system for network intrusion detection and classification", 9th International Conference on Soft Computing Models in Industrial and Environmental Applications, Bilbao, Spain, 25th - 27th Jun, 2014.

Date Presented:

25th - 27th Jun

A multi-agent arti cial immune system for network intrusion
detection and classi cation is proposed and tested in this paper. The
multi-layer detection and classi cation process is proposed to be executed
on each agent, for each host in the network. The experiment shows very
good results in detection layer, where 90% of anomalies are detected. For
the classi cation layer, 88% of false positives were successfully labeled
as normal trac connections, and 79% of DoS and Probe attacks were
labeled correctly. An analysis is given for future work to enhance results
for low-presented attacks.

Tourism