Assessing the effectiveness of artificial neural networks on problems related to elliptic curve cryptography

Cryptographic systems based on elliptic curves have been introduced as an alternative to conventional public key cryptosystems. The security of both kinds of cryptosystems relies on the hypothesis that the underlying mathematical problems are computationally intractable, in the sense that they cannot be solved in polynomial time. In this paper, we study the performance of artificial neural networks on the computation of a Boolean function derived from the use of elliptic curves in cryptographic applications. c © 2007 Elsevier Ltd. All rights reserved.