Toward Effective Network Traffic Analytics of Mobile Apps via Deep Learning
In recent years operators have experienced the tremendous growth of the traffic to be managed in their networks, whose heterogeneous composition (e.g. mobile/IoT devices, anonymity tools), dynamicity and increasing encryption is posing new challenges toward actionable network traffic analytics.
In this talk, the topics of network traffic classification and prediction generated by mobile applications will be covered, due to their beneficial use in network management, user-tailored experience and privacy. First, the reasoned use of Deep Learning umbrella will be introduced and explained in such context. Hence, lessons learned and common pitfalls will be highlighted. Subsequently, the adoption of sophisticated multi-modal multi-task architectures will be put forward. The objective is to devise AI-based traffic analysis tools able to capitalize the structured nature of traffic and able to support different objectives. The talk will also cover the current research done in the area of AI-based network traffic analysis at TRAFFIC group of University of Naples Federico II, Italy.
Speakers, Panelists and Moderators
DOMENICO CIUONZOAssistant ProfessorDIETI, University of Naples, Federico IIDomenico Ciuonzo received the B.Sc. and M.Sc. (summa) degrees in computer engineering and the Ph.D. degree from the University of Campania "L. Vanvitelli", Aversa, Italy, in 2007, 2009, and 2013, respectively. Since 2011, he has held several visiting appointments: NATO CMRE, IT (2011); ECE Department, University of Connecticut, US (2012); Department of Electronics and Telecommunications, NTNU, Trondheim, NOR (2015 and 2016); Centre Tecnològic de Telecomunicacions de Catalunya (CTTC), Castelldefels, ES (2018). His reviewing activities were recognized by the IEEE Communications Letters (in '13, '17 and '19), IEEE Trans. on Communications (in '14), IEEE Trans. on Instrumentation and Measurement (in '16), IEEE Transactions on Wireless Communications (in '17 and '18) and MDPI Sensors (in '17), which nominated him Exemplary Reviewer. He also received a similar recognition (“Top Reviewers” Award) for the whole MDPI publisher in 2017. Furthermore, his editorial activities were recognized by the IEEE Communications Letters, which nominated him Best Editor in '18 and '19, respectively. Since ‘14 he has served as Associate Editor for several IET, Elsevier and IEEE journals. Currently, he is also an Area Editor for the IEEE Transactions on Aerospace and Electronic Systems and the IEEE Communications Letters. His research interests fall within the areas of data fusion, network traffic analysis, statistical signal processing, IoT and wireless sensor networks and wireless communications. Domenico Ciuonzo has co-authored 85+ journal and conference publications within highly-reputed venues. Since 2016 he is an IEEE Senior Member. In '19, he received the Best Paper Award at 4th IEEE ICCCS. In '19, he was the recipient of the "Exceptional Service Award", from IEEE Aerospace and Electronic Systems Society (AESS). In '20 he received the "Technical Achievement Award", from IEEE Sensors Council for the area Sensor Systems or Networks (early career). In '20, he received the Best Paper Award from Elsevier Computer Networks for the publication “MIMETIC: Mobile Encrypted Traffic Classification using Multimodal Deep Learning“. He is co-author of the book “Data Fusion in Wireless Sensor Networks: A Statistical Perspective”, published by the IET (Apr. 2019). D. Ciuonzo has served and serves as independent reviewer/evaluator of research and implementation projects and project proposals co-funded by many EU and non-EU parties.