Machine Learning-Based Profiling Attack Method in RSA Prime Multiplication
Han-Byeol Park, Bo-Yeon Sim, Dong‐Guk Han · 2020
In this paper, we propose a machine learning-based profiling attack on the prime multiplication operation of RSA's key generation algorithm. The proposed attack takes advantage of the fact that a prime word value, which is the data storage unit, is loaded in the process of the multiplication operation for generating a modulus. We selected a commonly used product-scanning method as a multiplication algorithm. Then we collected the power consumption traces and constructed a profile of the secret prime value based on machine learning. In addition, the success rate of the attack was measured within a single trace to perform a realistic attack during the key generation operation. The secret prime values were derived with a maximum success rate of 99.8% in a single trace. Based on this, this paper suggests that if the secret value is an operand of the multiplication operation, there may be vulnerability against side-channel attacks because of the characteristics of the multiplication algorithm.1