DFIR Stream 0x2 

"Securing the IoT: Harnessing Deep Learning for Robust and Interpretable Intrusion Detection" 

by Dr. Antonio Montieri and Dr. Domenico Ciuonzo, University of Naples Federico II.

Abstract: In recent years, IoT traffic proliferation has been exponential and is poised for further escalation. With IoT devices being vulnerable targets for cyber-attacks, there is an urgent need for advanced and robust security tools in this vertical. Deep learning (DL) methods show promise for developing network intrusion detection systems (NIDSs) tailored to this challenge. However, traditional DL model training and evaluation relies on data from a single organization's network, limiting real-world performance assessment. Ensuring DL models work across diverse network environments is crucial. This lecture explores crafting effective, reliable, and resilient attack traffic classifiers using DL within IoT networks. We delve into intricate design considerations encompassing various single-modal and multimodal DL approaches, fueled by meticulously curated and unbiased input data tailored explicitly for IoT attack classification, facilitating early traffic classification. We also examine the interpretability of these methods, evaluating the impact of network layer fields on performance and potential biases. Additionally, we introduce a cross-evaluation methodology to assess models' ability to distinguish malicious from benign traffic across varied networks. We explore the influence of informative traffic fields on DL model generalisation. Furthermore, the lecture provides a practical segment guiding participants in designing, implementing, and evaluating NIDSs using Python frameworks.

Stream Outline:

1. General Introduction to Network Security in IoT Contexts.

2. Limitations of existing proposals.

3. Design Principles for Robust & Interpretable IDSs for IoT Settings.

4. Brief introduction to the design and implementation of IoT-focused NIDSs.

About the Speakers

Antonio Montieri is an Assistant Professor at the Department of Electrical Engineering and Information Technologies of the University of Napoli Federico II. He received his Ph.D. degree in Information Technology and Electrical Engineering in April 2020 and his MS Degree in Computer Engineering in July 2015, both from the same University. Antonio serves as an Associate Editor for the IEEE Open Journal of the Communications Society. He also participates in the editorial board of four further sector journals published by Frontiers, MDPI, and OAE Publishing. He serves as a reviewer for various international conferences and journals. His research interests concern network security, network measurements, (encrypted and mobile) traffic classification, traffic modeling and prediction, and eXplainable Artificial Intelligence (XAI) approaches for networks. Antonio has co-authored more than 50 papers in top-notch international journals and conference proceedings. For his research activity, Antonio Montieri has obtained various awards and grants. In particular, he was awarded the Computer Networks 2020 Best Paper Award for “MIMETIC: Mobile Encrypted Traffic Classification using Multimodal Deep Learning”, the Best Paper Award for “MIRAGE: Mobile-app Traffic Capture and Ground-truth Creation” at the 4th IEEE International Conference on Computing, Communications and Security (ICCCS 2019), and the Best Poster Award for “A Platform for Monitoring Public Cloud Networks” at the TMA (Traffic Monitoring and Analysis) Ph.D. School 2016.

Domenico Ciuonzo is a Tenure-Track Assistant Professor at the University of Naples Federico II, Italy. He received his Ph.D. in 2013 from Univ. of Campania. He has held the following visiting appointments: NATO CMRE (IT), UCONN (US), NTNU (NOR), and CTTC (ES). He is a Track-Chair for IEEE WCNC 2024, a publication chair for IEEE TMA 2023, an elected member of the IEEE SPS SPCOM technical committee, and a member of the “Conferences and Events Committee” of the IEEE IoT Technical Community. He has served as Associate EiC for the IEEE Comm. Letters, Tech. Editor for the IEEE Trans. on Aerospace and Electronic Systems, Lead Guest Editor for the IEEE IoT Magazine. His reviewing and editorial activities were recognized by the IEEE Comm. Letters, IEEE Trans. on Comm., IEEE Trans. on Wireless Comm., and MDPI, which nominated him as Exemplary Reviewer and Editor for 14 times. He is the recipient of two Best Paper awards (IEEE ICCCS 2019 and Elsevier Computer Networks 2020), the 2019 Exceptional Service award from IEEE AESS, the 2020 Early-Career Technical Achievement award from IEEE SENSORS COUNCIL for sensor networks/systems, and the 2021 Early-Career Award from IEEE AESS. His research interests fall within the areas of data fusion, network traffic analysis, statistical signal processing, IoT & wireless sensor networks, and AI. He has co-authored 130+ journal and conference publications to top-notch venues. He is co-author of the IET book “Data Fusion in Wireless Sensor Networks: A Statistical Signal Processing Perspective”. Since 2016 he is an IEEE Senior Member. D. Ciuonzo is the co-PI of the PRIN-22 “GARDEN” and serves as an independent reviewer/evaluator of research and implementation projects and project proposals co-funded by many EU and non-EU parties. 

Date and Time: Friday, March 1 · 2:00 – 3:00 pm (GMT+00:00) United Kingdom Time

Location:  Online (Pre-Registration is Required to Obtain the Meeting Link)

Event Registration Link:  https://forms.gle/MYSHvETpR4zEAtF76 

Online Registration Ends February 28 at 04:00 PM (GMT+00:00) United Kingdom Time

Recording