The transformative potential of AI in enhancing computer science solutions has not gone unnoticed in the fields of security and privacy. However, the sheer volume of related scientific literature and the significant gap between a lab context and real-world environments make it extremely challenging to assess the current progress in the area. In this talk, we will review main underlying principles and common pitfalls behind deep learning solutions when applied to offensive and defensive cybersecurity. The focus will be set on three use cases: anonymous Tor traffic re-identification, network intrusion detection and malware detection. The discussion will challenge the common (mis)perception of the purely end-to-end functionality of advanced AI.


Dr. Vera Rimmer, KU Leuven
Dr. Vera Rimmer is a research expert at the DistriNet research group at KU Leuven, where she conducts and leads research activities in the intersection of security, privacy and AI. She completed her PhD at KU Leuven in 2022, with the main focus on applying deep learning in anonymity networks and network defense systems. Currently, Vera and her team explore data analytics in network intrusion and malware detection, and trustworthiness of data-driven AI in the wider ICT context. Vera is interested in developing comprehensive understanding, reasonable expectations and mitigation of risks of data-driven AI in the age of uncontrolled data collection and inference.


Program
2.00 pm – 2.05 pm: Introduction
2.05 pm – 3.00 pm: Presentation
3.00 pm – 3.30 pm: Q&A
3.30 pm – 4.30 pm: Apéro