Abstract
It is proposed an agent approach for creation of intelligent intrusion detection system. The system allows detecting known type of attacks and anomalies in user activity and computer system behavior. The system includes different types of intelligent agents. The most important one is user agent based on neural network model of user behavior. Proposed approach is verified by experiments in real intranet of Institute of Physics and Technologies of National Technical University of Ukraine "Kiev Polytechnic Institute.
Highlights
At present the urgency of information security issue has increased greatly
Today there is a great number of commercial Intrusion Detection Systems (IDS)
Its aim is to reveal regularities between inputs and outputs. The learning of such type of neural network consist in minimization of error functional by gradient descent method
Summary
At present the urgency of information security issue has increased greatly. Today there is a great number of commercial Intrusion Detection Systems (IDS). The well-known existing IDS representatives are Haystack, MIDAS, ASAX, etc. Those systems, while contributing pioneer solutions to the security field, possess certain key drawbacks: 1. The probabilities of false positives and false negatives are too high. 2. Detection of previously unknown types of attacks is unlikely
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have