Impact of Nonbinary Input Vectors on Security of Tree Parity Machine

Key agreement protocol is an essential step for establishing a secure connection. The inevitable advancements in quantum computing technologies pose a huge threat to the key agreement protocol in use today. Neural cryptography is an alternative key agreement protocol that is not susceptible to any known quantum algorithm. Since the invention of mutual learning of TPM, many improvements have been proposed. One of them was the usage of nonbinary input vectors. This study verifies the impact of nonbinary input vectors on TPM security features. A number of iterations, similarity to intruder’s TPM and effective key length were taken into account. The results show that the choice between fast synchronization times and higher security of the final key must be performed with perfect care.