Into the Unknown: Unsupervised Machine Learning Algorithms for Anomaly-Based Intrusion Detection
Tommaso Zoppi, Andrea Ceccarelli, Andrea Bondavalli · 2020
Anomaly detection aims at identifying patterns in data that do not conform to the expected behavior, relying on machine-learning algorithms that are suited for binary classification. It has been arising as one of the most promising techniques to suspect intrusions, zero-day attacks and, under certain conditions, failures. This tutorial aims to instruct the attendees to the principles, application and evaluation of anomaly-based techniques for intrusion detection, with a focus on unsupervised algorithms, which are able to classify normal and anomalous behaviors without relying on input data with labeled attacks.