Abstract. In this paper, a detail analysis of Tree Parity Machine (TPM) and Double Hidden Layer Perceptron (DHLP) based session key exchange tecchnique has been presented in terms of synchronization time, space complexity, variability of learning rules, gantt chart, total number of threads and security. TPM uses single hidden layer in their architecture and participated in mutual learning for producing the tuned weights as a session key. DHLP uses two hidden layers instead of single. Addition of this extra layer enhances the security of the key exchange protocol. Comparisons of results of both techniques has been presented along with detail analysis.Keywords: Tree Parity Machine (TPM), Double Hidden Layer Perceptron (DHLP), session key, wireless communication.
IntroductionThese days a range of techniques are available to exchange session key. Each technique has its own advantages and disadvantages. In key exchange the main security intimidation is Man-In-The-Middle (MITM) attack at the time of exchange the secret session key over public channel. Diffie-Hellman key exchange algorithm suffers from this MITM attack. Most of the key generation algorithms in Public-Key cryptography suffer from MITM attack [1]. Where intruders can reside middle of sender and receiver and tries to capture all the information transmitting from both parties. Another noticeable problem is that most of the key generation algorithms need large amount of memory space for storing the key but now-a-days most of the handheld wireless devices have a criterion of memory constraints. In proposed DHLPSKG, problem MITM attack of Diffie-Hellman Key exchange [1] has been set on. In TPM and DHLP based session key generation procedure, both sender and receiver use identical architecture. Both of these DHLP [2] and TPM's [3,4,5,6,7] start with random weights and identical input vector. The organization of this paper is as follows. Section 2 of the paper deals with the TPM synchronization algorithm. DHLP based protocol for generation of session key