Multivariate Cryptography Based on Clipped Hopfield Neural Network

• Published in: IEEE transaction on neural networks and learning systems 2018-02, Vol.29 (2), p.353-363
• Main Authors: Wang, Jia, Cheng, Lee-Ming, Su, Tong
• Format: Article
• Language: English
• Subjects: Algorithms; Clipped Hopfield neural network (CHNN); Computer applications; Computer simulation; Computer systems; Cryptography; Data encryption; Elliptic curve cryptography; Feasibility studies; multivariate cryptography (MVC); Neural networks; Neurons; postquantum cryptography; public key cryptography; Public Key Infrastructure; Quantum computing; Security
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2016.2626466

Designing secure and efficient multivariate public key cryptosystems [multivariate cryptography (MVC)] to strengthen the security of RSA and ECC in conventional and quantum computational environment continues to be a challenging research in recent years. In this paper, we will describe multivariate public key cryptosystems based on extended Clipped Hopfield Neural Network (CHNN) and implement it using the MVC (CHNN-MVC) framework operated in \text {GF}(p) space. The Diffie-Hellman key exchange algorithm is extended into the matrix field, which illustrates the feasibility of its new applications in both classic and postquantum cryptography. The efficiency and security of our proposed new public key cryptosystem CHNN-MVC are simulated and found to be NP-hard. The proposed algorithm will strengthen multivariate public key cryptosystems and allows hardware realization practicality.