The evaluation of the TPM synchronization on the basis of their outputs

Purpose: Tree Parity Machines are specific artificial neural networks used to construct relatively secure key exchange protocol [12,15,24]. The level of networks’ compatibility is measured by weight vectors mutual overlap. However, to calculate such mutual overlap, one needs to be familiar with both weights’ vectors, which is impossible in practical key exchange. This paper discusses other schemes to evaluate compatibility of weights’ vectors. The first one uses Euclidean distance of both weights’ vectors. The second one is based on frequencies of common TPM’s outputs and as such does not rely on the weights’ vectors. Both approaches to handle secure key exchange protocol facilitate more extended analysis of many technical processes in which a vital role plays an incorporation of a non-standard high-quality method securing any sensitive data. Design/methodology/approach: Computer simulations of TPM synchronization are conducted using authors’ program and the obtained results are statistically analyzed herein. Findings: We found experimentally that mutual overlap of the weights’ vectors is highly correlated with Euclidean distance. Additionally, frequencies of common outputs in given numbers of learning cycles stay in high correlation with this mutual overlap and Euclidean distance. The latter can subsequently be used to draw pertinent conclusions about TPM’s weights compatibility. Practical implications: Proposed methods, especially frequencies analysis, can be applied to key exchange protocol to improve its security. Determining the vectors compatibility level before synchronization completion allows qualifying this synchronization to one of the possible time classes. Originality/value: New ideas presented in this work involve application of Euclidean distance and common output frequencies to calculate the networks compatibility given by weights mutual overlap.