2009/10/16 by Gianni Tedesco, Tedesco, Gianni, Uwe Aickelin +1
Computer Science · Engineering · #Advanced Malware Detection Techniques #Artificial Immune Systems Applications #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Network Security and Intrusion Detection #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.0910.3124
openalex publication_date 2009/10/16 · openalex created_date 2022/09/29 · openalex updated_date 2026/07/28
Network Intrusion Detection Systems (NIDS) are computer systems which monitor\na network with the aim of discerning malicious from benign activity on that\nnetwork. While a wide range of approaches have met varying levels of success,\nmost IDSs rely on having access to a database of known attack signatures which\nare written by security experts. Nowadays, in order to solve problems with\nfalse positive alerts, correlation algorithms are used to add additional\nstructure to sequences of IDS alerts. However, such techniques are of no help\nin discovering novel attacks or variations of known attacks, something the\nhuman immune system (HIS) is capable of doing in its own specialised domain.\nThis paper presents a novel immune algorithm for application to the IDS\nproblem. The goal is to discover packets containing novel variations of attacks\ncovered by an existing signature base.\n