Pseudo random number generators (PRNGs) are one of the most important components in security and cryptography applications. We propose an application of Hopfield Neural Networks (HNN) as pseudo random number generator. This research is done based on a unique property of HNN, i.e., its unpredictable behavior under certain conditions. Also, we propose an application of Fuzzy Hopfield Neural Networks (FHNN) as pseudo random number generator. We compare the main features of ideal random number generators with our proposed PRNGs. We use a battery of statistical tests developed by National Institute of Standards and Technology (NIST) to measure the performance of proposed HNN and FHNN. We also measure the performance of other standard PRNGs and compare the results with HNN and FHNN PRNG. We have shown that our proposed HNN and FHNN have good performance comparing to other PRNGs accordingly.

Developing pseudo random number generator based on neural networks and neurofuzzy systems

Confirmation of the existence of complex behavior and synchronization of non-identical chaotic systems as
reported in literature attracts much interest in secure communication, but practical implementation is still
challenging. In this work, the dynamics of coupled non-identical circuits comprising periodically forced
Duffing and Van der Pol oscillators is investigated via electronic simulation using Multism software and
hardware implementation on electronic circuits board. After complete synchronization is achieved between the
Duffing (Transmitter) and Van der Pol (receiver) circuits through the variation of the coupling
resistor of the controller, its application to secure communication is therefore demonstrated experimentally and
via multism. The results from the electronic simulation and hardware implementation on bread board using
analog components are in good agreement with the numerical results in literature.
Keywords: Electronic simulation, Periodically Forced Duffing oscillator, Periodically Forced
Van
der Pol oscillator, Secure Communication, Synchronization

/pdf/electronic-simulation-and-hardware-implementation-of-82aq47byr4.pdf

Electronic Simulation and Hardware Implementation of TwoCoupled Periodically Forced Duffing and Van der Poloscillators and its Application to Secure Communication

In this paper we present a new and effective attack strategy on neural cryptography. The neural cryptosystem has been recently shown to be secure under some different attack strategies. But all these attack strategies aim at the mechanism of the secret key generated by the global dynamics of two interacting neural networks. The strategy we propose focuses on the authentication which the neural cryptosystem takes little account of. The proposed authenticated key exchange mechanisms are analyzed and convinced to be hardly applicable.

Ping Li

Papers

Compound Attack on Synchronization Based Neural Cryptography