Visible to the public Host-based Intrusion Detection Systems Inspired by Machine Learning of Agent-Based Artificial Immune Systems

TitleHost-based Intrusion Detection Systems Inspired by Machine Learning of Agent-Based Artificial Immune Systems
Publication TypeConference Paper
Year of Publication2019
AuthorsOu, Chung-Ming
Conference Name2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)
KeywordsAAIDS, adaptable agent-based IDS, AG agent, agent-based artificial immune systems, artificial immune system, artificial immune systems, composability, Computational modeling, Computer hacking, computer network security, danger theory, DC agent, dendritic cell, dendritic cells, host-based intrusion detection systems, Immune system, Intrusion detection, Intrusion Detection Systems, learning (artificial intelligence), Learning systems, machine learning, multi-agent systems, multiagents system, network packets, pubcrawl, Resiliency, TC agent
Abstract

An adaptable agent-based IDS (AAIDS) inspired by the danger theory of artificial immune system is proposed. The learning mechanism of AAIDS is designed by emulating how dendritic cells (DC) in immune systems detect and classify danger signals. AG agent, DC agent and TC agent coordinate together and respond to system calls directly rather than analyze network packets. Simulations show AAIDS can determine several critical scenarios of the system behaviors where packet analysis is impractical.

DOI10.1109/INISTA.2019.8778269
Citation Keyou_host-based_2019