Soft Computing in Cryptography

Abstract:

We discuss several applications of metaheuristics and machine learning in cryptography. We start with a brief introduction to machine learning and metaheuristic techniques and then, we focus on several practical case studies.  First, we consider difficult optimization problems such as designing S-boxes with good cryptographic and implementation properties (with specific emphasis on area and power). We discuss in particular how to use population based metaheuristic techniques (such as evolutionary computation) in the design process. Next, we investigate how to use machine learning in side-channel attacks, elaborating on a life-cycle of a machine learning process with an example application taken from the DPA contest site.

Finally, we introduce several possible future research avenues.

Biography:

Stjepan Picek is a postdoctoral researcher in the Computer Security and Industrial Cryptography (COSIC) group at KU Leuven, Belgium. His research interests are cryptography, machine learning, and evolutionary computation. He completed his PhD in 2015 under the supervision of Lejla Batina, Elena Marchiori, and Domagoj Jakobovic Stjepan is member of the organization committee for International Summer School in Cryptography and the vice-president of the Croatian IEEE CIS Chapter and serves as a reviewer for several journals and conferences.