INSOMNIA
Giuseppina Andresini, Feargus Pendlebury, Fabio Pierazzi, Corrado Appice Annalisa Malerba Donato Loglisci, Annalisa Appice, Lorenzo Cavallaro
Abstract
Despite decades of research in network traffic analysis and incredible advances in artificial intelligence, network intrusion detection systems based on machine learning (ML) have yet to prove their worth. One core obstacle is the existence of concept drift, an issue for all adversary-facing security systems. Additionally, specific challenges set intrusion detection apart from other ML-based security tasks, such as malware detection.
Topics & Concepts
Intrusion detection systemComputer scienceMalwareComputer securityArtificial intelligenceAdversaryCore (optical fiber)Network securityObstacleSet (abstract data type)Intrusion prevention systemMachine learningTelecommunicationsLawPolitical scienceProgramming languageNetwork Security and Intrusion DetectionInternet Traffic Analysis and Secure E-votingAnomaly Detection Techniques and Applications