Selection of Deep Neural Network Models for IoT Anomaly Detection Experiments
Diana Gaifulina, Igor Kotenko
Abstract
This research is about selection of deep neural network models for anomaly detection in Internet of Things network traffic. We are experimentally evaluating deep neural network models using the same software, hardware and the same subsets of the UNSW-NB 15 dataset for training and testing. The assessment results are quality metrics of anomaly detection and the time spent on training models.
Topics & Concepts
Anomaly detectionComputer scienceArtificial neural networkAnomaly (physics)Selection (genetic algorithm)Artificial intelligenceSoftwareDeep learningMachine learningData miningDeep neural networksOperating systemCondensed matter physicsPhysicsNetwork Security and Intrusion DetectionAnomaly Detection Techniques and ApplicationsSmart Grid Security and Resilience