Biblio

Neural networks based cryptography has seen a significant growth since the introduction of adversarial cryptography which makes use of Generative Adversarial Networks (GANs) to build neural networks that can learn encryption. The encryption has been proven weak at first but many follow up works have shown that the neural networks can be made to learn the One Time Pad (OTP) and produce perfectly secure ciphertexts. To the best of our knowledge, existing works only considered communications between two or three parties. In this paper, we show how multiple neural networks in an adversarial setup can remotely synchronize and establish a perfectly secure communication in the presence of different attackers eavesdropping their communication. As an application, we show how to build Secret Sharing Scheme based on this perfectly secure multi-party communication. The results show that it takes around 45,000 training steps for 4 neural networks to synchronize and reach equilibria. When reaching equilibria, all the neural networks are able to communicate between each other and the attackers are not able to break the ciphertexts exchanged between them.

The rapid rate of change in technology and the increasing sophistication of cyber attacks require any organization to have a continuous preparation. However, the resource and time intensive nature of cybersecurity education and training renders traditional approaches highly inefficient. Simulators have attracted the attention in the last years as a potential solution for cybersecurity training. However, in spite of the advances achieved, there is still an urgent need to address some open challenges. In this paper we present a novel simulator that solves some these challenges. First, we analyse the main properties that any cybersecurity training solution should comprise, and evaluate to what extent training simulators can meet them. Next, we introduce the functional architecture and innovative features of the simulator, of which a functional prototype has already been released. Finally, we demonstrate how these capabilities are put into practice in training courses already available in the simulator.