Paper 2019/144

Modeling Power Efficiency of S-boxes Using Machine Learning

Rajat Sadhukhan, Nilanjan Datta, and Debdeep Mukhopadhyay

Abstract

In the era of lightweight cryptography, designing cryptographically good and power efficient 4x4 S-boxes is a challenging problem. While the optimal cryptographic properties are easy to determine, verifying the power efficiency of an S-box is non-trivial. The conventional approach of determining the power consumption using commercially available CAD-tools is highly time consuming, which becomes formidable while dealing with a large pool of S-boxes. This mandates development of an automation that should quickly characterize the power efficiency from the Boolean function representation of an S-box. In this paper, we present a supervised machine learning assisted automated framework to resolve the problem for 4x4 S-boxes, which turns out to be 14 times faster than traditional approach. The key idea is to extrapolate the knowledge of literal counts, AND-OR-NOT gate counts in SOP form of the underlying Boolean functions to predict the dynamic power efficiency. The experimental results and performance of our novel technique depicts its superiority with high efficiency and low time overhead. We demonstrate effectiveness of our framework by reporting a set of power efficient optimal S-boxes from a large set of S-boxes. We also develop a deterministic model using results obtained from supervised learning to predict the dynamic power of an S-box that can be used in an evolutionary algorithm to generate cryptographically strong and low power S-boxes.