Mutual learning in a tree parity machine and its application to cryptography
Authors:
- 30 December 2002
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 66 (6) , 066135
Abstract
Mutual learning of a pair of tree parity machines with continuous and discrete weight vectors is studied analytically. The analysis is based on a mapping procedure that maps the mutual learning in tree parity machines onto mutual learning in noisy perceptrons. The stationary solution of the mutual learning in the case of continuous tree parity machines depends on the learning rate where a phase transition from partial to full synchronization is observed. In the discrete case the learning process is based on a finite increment and a full synchronized state is achieved in a finite number of steps. The synchronization of discrete parity machines is introduced in order to construct an ephemeral key-exchange protocol. The dynamic learning of a third tree parity machine (an attacker) that tries to imitate one of the two machines while the two still update their weight vectors is also analyzed. In particular, the synchronization times of the naive attacker and the flipping attacker recently introduced in Ref. 9 are analyzed. All analytical results are found to be in good agreement with simulation results.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Secure exchange of information by synchronization of neural networksEurophysics Letters, 2002
- On-line learning in the Ising perceptronJournal of Physics A: General Physics, 2000
- Interacting neural networksPhysical Review E, 2000
- Dynamics of interacting neural networksJournal of Physics A: General Physics, 2000
- On-line learning in a discrete state spaceJournal of Physics A: General Physics, 1998
- On-line learning in parity machinesJournal of Physics A: General Physics, 1996
- Training Binary Perceptrons by ClippingEurophysics Letters, 1995
- Statistical physics estimates for the complexity of feedforward neural networksPhysical Review E, 1995
- Clipped-Hebbian Training of the PerceptronEurophysics Letters, 1993
- Statistical mechanics of a multilayered neural networkPhysical Review Letters, 1990