Permutation parity machines for neural synchronization

Synchronization of neural networks has been studied in recent years as an alternative to cryptographic applications such as the realization of symmetric key exchange protocols. This paper presents a first view of the so-called permutation parity machine, an artificial neural network proposed as a binary variant of the tree parity machine. The dynamics of the synchronization process by mutual learning between permutation parity machines is analytically studied and the results are compared with those of tree parity machines. It will turn out that for neural synchronization, permutation parity machines form a viable alternative to tree parity machines.

[1]  Wolfgang Kinzel,et al.  Mutual learning in a tree parity machine and its application to cryptography. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  Jürgen Kurths,et al.  Synchronization - A Universal Concept in Nonlinear Sciences , 2001, Cambridge Nonlinear Science Series.

[3]  I Kanter,et al.  Secure key-exchange protocol with an absence of injective functions. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[4]  W. Kinzel,et al.  Secure exchange of information by synchronization of neural networks , 2002 .

[5]  Jürgen Kurths,et al.  Synchronization: Phase locking and frequency entrainment , 2001 .

[6]  Andreas Ruttor,et al.  Neural cryptography with feedback. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1951 .

[8]  Markus Volkmer,et al.  Tree parity machine rekeying architectures , 2005, IEEE Transactions on Computers.

[9]  Marius Iosifescu,et al.  Finite Markov Processes and Their Applications , 1981 .