Distributed Anomaly Detection System as a Service using Statistical Learning for Industrial IoT-Edge-Cloud NetworksSpeaker: Nour Moustafa – Canberra, ACT, Australia
Topic(s): Security and Privacy
AbstractAs Industrial Internet of Things (IIoT) systems have become more commonplace, there are various data management and security monitoring tools deployed at the cloud for logging and inspecting data generated by IIoT devices and systems. There have also been recent trends to move the tools to the edge of a network to overcome known limitations in cloud-based solutions, such as latency and security issues. However, protecting edge networks against zero-day attacks is challenging due to the volume, variety and veracity of data collected from the broad types of IIoT devices. In this paper, we suggest a Distributed Anomaly Detection (DAD) system as a service for discovering cyber-attacks from IIoT-edge-cloud networks. The proposed system is developed using a novel statistical learning mechanism, Gaussian Mixture-based Correntropy. This system is designed to effectively monitor and recognize zero-day attacks in real-time. We also propose an IIoT-edge-cloud architecture that presents the deployment of the proposed system at network gateways. The proposed system is evaluated using the NSL-KDD and UNSW-NB15 datasets. The findings revealed that the proposed system achieves better performances, in terms of detection accuracy and processing time, compared with peer techniques.
About this LectureNumber of Slides: 25
Duration: 60 minutes
Languages Available: English
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.