2004/11/30 by Andreas Ruttor, Wolfgang Kinzel, Ido Kanter
Computer Science · Physics and Astronomy · #Adversarial Robustness in Machine Learning #Chaos-based Image/Signal Encryption #Cryptography and Data Security #cond-mat.dis-nn
paper · pdf · doi:10.1088/1742-5468/2005/01/p01009
published as J. Stat. Mech. (2005) P01009 · 12 pages, 8 figures; typos corrected
openalex publication_date 2005/01/25 · arxiv created 2005/03/01 · arxiv updated 2009/12/01 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/30
Neural cryptography is based on synchronization of tree parity machines by mutual learning. We extend previous key-exchange protocols by replacing random inputs with queries depending on the current state of the neural networks. The probability of a successful attack is calculated for different model parameters using numerical simulations. The results show that queries restore the security against cooperating attackers. The success probability can be reduced without increasing the average synchronization time.