Attack on lattice shortest vector problem using K-Nearest Neighbour

Lattice-based cryptography is now the most effective and adaptable branch of post-quantum cryptography. The prime number factoring assumption or the presumption that the discrete logarithm problem is intractable are the two assumptions that underlie nearly all cryptographic security systems. Lattice-based cryptography has recently gained popularity to improve security as the world prepares for quantum computing. Lattices are used to secure the systems; however, one of the problems is the Shortest vector problem. In this work, we addressed the attack on lattice problems, especially two-dimensional, four-dimensional, and ten-dimensional, with the help of the machine learning algorithm K-Nearest Neighbour (KNN). Results and analysis findings demonstrate that the suggested approach can achieve accuracy of upto 78% and 58% on self-prepared datasets over two-dimensional and ten- dimensional, respectively.