Lattice Reduction Using K-Means Algorithm

In post-quantum encryption, lattice-based cryptography has become the most powerful and adaptable subfield. Traditional cryptographic systems, including RSA and DSA, are based on the notion that discrete and prime number logarithms are intractable. However, quantum computing threatens to undermine these assumptions. Cryptography based on lattices has grown in popularity as a reliable solution to overcome this obstacle. There are several mathematical problems used in cryptography, including the well-known Shortest Vector Problem (SVP) of lattices. So far, this work focuses on approaches to lattice issues, particularly in two-dimensional and four-dimensional spaces. Unsupervised ML technique K-Means Clustering splits the unlabeled dataset into various clusters. In order to ensure that the data points within each group are more comparable to one another than the data points within the other groups, clustering aims to divide the population into a number of groups. In a nutshell, it’s a collection of items with both similarities and differences .K-means to reduce the size of Lattice. K-means machine learning (ML) is used to accomplish this. On datasets that we prepared ourselves, our findings and analyses show a 60% accuracy rate for the strategy we discussed in this paper. A contribution of this study is to enhance lattice-based cryptography's security against emerging threats, particularly in the context of quantum computing.