Paper ID: 2402.19254

Machine learning for modular multiplication

Kristin Lauter, Cathy Yuanchen Li, Krystal Maughan, Rachel Newton, Megha Srivastava

Motivated by cryptographic applications, we investigate two machine learning approaches to modular multiplication: namely circular regression and a sequence-to-sequence transformer model. The limited success of both methods demonstrated in our results gives evidence for the hardness of tasks involving modular multiplication upon which cryptosystems are based.

Submitted: Feb 29, 2024