The most powerful and adaptable subfield of post-quantum encryption has come to be known as lattice-based cryptography. Traditional cryptographic systems, including RSA and DSA, are predicated on ideas like the supposed intractability of the discrete and prime number difficulties with logarithms. However, these presumptions are threatened by the introduction of quantum computing. To overcome this obstacle, lattice-based as a reliable solution, cryptography has grown in popularity. In this cryptographic paradigm, one of the major obstacles is the problem of the shortest vector (SVP). This paper focuses on addressing approaches to lattice issues, especially in two-dimensional up to four-dimensional spaces. In order to do this, we use the K-means machine learning (ML) technique. In this paper, findings and analyses show that the strategy we've suggested can reach an accuracy of 60% on datasets that we have prepared ourselves. This study offers a contribution to enhancing lattice-based cryptography’s security against emerging threats, especially in the quantum computing context.
shaurya010/Reducing-the-Size-of-the-Lattice-using-K-Means
Reducing-the-Size-of-the-Lattice-using-K-Means
Jupyter Notebook