Seminar: Network traffic anomaly detection and analysis

22/03/2023 -


On 22nd March 2023 at 10:0h the CTTC will host the seminar “Network traffic anomaly detection and analysis”. In this seminar Valentina Timcenko, Ph.D. Research Associate will present:


This research presents an overview of the exploration, development and implementation of the network traffic behavior analysis and provides a comprehensive flow-based anomaly detection solution. The proposal relies on the combined application of entropy-based and machine learning anomaly detection techniques.
Starting from the application of the entropy-based approach, the research reveals the results of methodical work with a goal to solve the main challenges in designing an efficient anomaly detection solution empowered with the original classification method. The entropy-based analysis can capture the behavior of the biggest contributors, and of a large number of minor appearances in the feature distribution, thus it is applied for the needs of easier detection of the rare traffic patterns.
Next, the range of the machine learning algorithms can be applied in order to process the detected unusual traffic. The machine learning aproach relies on the understanding of the legitimate traffic behavior characteristics, which is further used to efficiently detect the anomalous traffic patterns and deviations that could cause performance issues or indicate a breach. This way, it is possible to provide the near real-time alerting and visibility of the potential network security threats. This way combined techniques allow the detection of the unknown threats, zero-day attacks, and suspicious behavior while providing the performance optimization possibilities.
Even at the minimum viable product stage, the proposed solution confirms high performances and great applicability of the anomaly detection and classification method in real-life network environments.


Valentina Timčenko received her Dipl. Eng., M.Sc. and Ph.D. degrees in electrical engineering from the School of Electrical Engineering, University of Belgrade, in 2004, 2010, and 2022, respectively. Her Ph.D. thesis is focused on the Network Attacks Detection Based On Traffic Flows Analysis Using Hybrid Machine Learning Algorithms. Her M.Sc. thesis was related to the Principles of the Security Simulations for the Mobile ad hoc Networks.
Her scientific and professional commitment includes research, design, and implementation of solutions for telecommunication networks, especially in the area of network security, intrusion detection and prevention systems, machine learning, internet of things and cloud computing.
Valentina Timčenko participated in several national and international projects (INTERACT, IRACON, SEE TV-WEB, POLICY ANSWERS, SINERGY). She is the reviewer and a member of technical and organization committee of a number of international conferences.
Valentina Timčenko published 116 publications and a large number of technical solutions. She is an IEEE member for 20 years. She is holding several Cisco certificates.

This talk is open to whoever interested from the research community

Live event: Click here

Venue: CTTC's Auditorium, Building B4, Av. Carl Friedrich Gauss, 7, PMT, 08860 Castelldefels (Barcelona) - 10:00h-