Dr. Stjepan Picek
Stjepan Picek is an assistant professor in the Cybersecurity group at TU Delft, The Netherlands. His research interests are security/cryptography, machine learning, and evolutionary computation. Before the assistant professor position, Stjepan was a postdoctoral researcher at MIT, USA, and KU Leuven, Belgium. Stjepan finished his Ph.D. in 2015 with a topic on cryptology and evolutionary computation techniques. Stjepan also has several years of experience working in industry and government. Up to now, Stjepan gave more than 15 invited talks at conferences and summer schools and published more than 80 refereed papers. Stjepan is a member of the organization committee for International Summer School in Cryptography and president of the Croatian IEEE CIS Chapter. He is a general co-chair for Eurocrypt 2020, an organizer for the Lorentz workshop on AI and security, program committee member and reviewer for several conferences and journals, and a senior IEEE member.
In the last few years, profiling side-channel analysis based on deep learning proved to be very successful in breaking cryptographic implementations. Still, despite successful attacks, even in the presence of various countermeasures, there are many open questions. While a large part of the research effort concentrates on improving the performance of attacks, little is done to understand them and, even more importantly, use that knowledge in the design of more secure implementations. In this talk, we first discuss the best success stories on deep learning-based side-channel analysis. Afterward, we concentrate on critical open questions and research directions that still need to be explored.