Approach to design neural cryptography: A generalized architecture and a heuristic rule

摘要

Neural cryptography, a type of public key exchange protocol, is widely considered as an effective methodnfor sharing a common secret key between two neural networks on public channels. How to design neuralncryptography remains a great challenge. In this paper, in order to provide an approach to solve this challenge, angeneralized network architecture and a significant heuristic rule are designed. The proposed generic frameworknis named as tree state classification machine (TSCM), which extends and unifies the existing structures, i.e.,ntree parity machine (TPM) and tree committee machine (TCM). Furthermore, we carefully study and find thatnthe heuristic rule can improve the security of TSCM-based neural cryptography. Therefore, TSCM and thenheuristic rule can guide us to designing a great deal of effective neural cryptography candidates, in which itnis possible to achieve the more secure instances. Significantly, in the light of TSCM and the heuristic rule, wenfurther expound that our designed neural cryptography outperforms TPM (the most secure model at present) onnsecurity. Finally, a series of numerical simulation experiments are provided to verify validity and applicability ofnour results.