North Carolina State
"Machine Learning and Side-Channel Analysis: Happily Ever After or Bitter Divorce?"
While machine learning helps automating and improving certain classification/regression tasks, side-channel analysis allows extracting secret information from systems that are mathematically secure. Although these were two fairly distinct research domains, they have recently been getting closer. Yet it is unclear how they would couple. In this talk, I will explain my research group's efforts in using machine learning for side channels, and side channels for machine learning. I will first demonstrate new side-channel attacks on machine-learning hardware that can steal valuable machine-learning models and methods for protection. Then, I will show the use of novel machine-learning techniques to outperform classical side-channel attacks and break cryptographic systems that cannot be broken with classical attacks.
Dr. Aysu is currently an assistant professor and Bennett Faculty Fellow at the Electrical and Computer Engineering Department of North Carolina State University, where he leads HECTOR: Hardware Cybersecurity Research Lab. He got his M.S. from Sabanci University in Istanbul, Turkey, and his Ph.D. from Virginia Tech. Before joining NC State, he was a post-doctoral researcher at the University of Texas at Austin. Dr. Aysu's interests are broadly in hardware security research and cybersecurity education. His hardware security research has won NSF CAREER, NSF CRII, Google RSP, and Goodnight Innovation Fellow awards, six best paper nominations (IACR TCHES, IEEE HOST, DATE, GLS-VLSI), two best paper awards, one hardware security top picks (IEEE CEDA), and one publicity paper award (DAC). He is an IEEE senior member.