Machine Learning Method with Applications in Hardware Security of Post-Quantum Cryptography

Machine learning (ML) is the core of Artificial Intelligence (AI), and it is the fundamental way to make computer have intelligence. ML is a technology that uses algorithms to parse data, constantly learn, and make judgements and predictions about what happens. With the continuous development of ML technology, using ML algorithms to analyze the security of physical hardware has gradually become one of the hot spots in the research field. In the field of hardware security, post quantum cryptography is one of the research hotspots, e.g., multivariate cryptography. However, analyzing post-quantum signatures based on ML is still in the early stage. As substitutions of current used signatures, post-quantum signatures should fully consider side channel attack based on ML techniques so that they can be used in reality. In order to address such challenges, we present ML techniques to exploit the measurement of side channel attacks to post-quantum signatures. We propose a ML model for the measurement of side channel attacks. The efficiency of the proposed model is measured and it can be extended to analyze other similar signatures.