Learning Perfectly Secure Cryptography to Protect Communications with Adversarial Neural Cryptography

Researches in Artificial Intelligence (AI) have achieved many important breakthroughs, especially in recent years. In some cases, AI learns alone from scratch and performs human tasks faster and better than humans. With the recent advances in AI, it is natural to wonder whether Artificial Neural Networks will be used to successfully create or break cryptographic algorithms. Bibliographic review shows the main approach to this problem have been addressed throughout complex Neural Networks, but without understanding or proving the security of the generated model. This paper presents an analysis of the security of cryptographic algorithms generated by a new technique called Adversarial Neural Cryptography (ANC). Using the proposed network, we show limitations and directions to improve the current approach of ANC. Training the proposed Artificial Neural Network with the improved model of ANC, we show that artificially intelligent agents can learn the unbreakable One-Time Pad (OTP) algorithm, without human knowledge, to communicate securely through an insecure communication channel. This paper shows in which conditions an AI agent can learn a secure encryption scheme. However, it also shows that, without a stronger adversary, it is more likely to obtain an insecure one.

[1]  Adi Shamir,et al.  Analysis of Neural Cryptography , 2002, ASIACRYPT.

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

[3]  Claude E. Shannon,et al.  Communication theory of secrecy systems , 1949, Bell Syst. Tech. J..

[4]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[5]  B. John Oommen,et al.  On the Cryptanalysis of Two Cryptographic Algorithms That Utilize Chaotic Neural Networks , 2015 .

[6]  D. Rao,et al.  Using Layer Recurrent Neural Network to Generate Pseudo Random Number Sequences , 2012 .

[7]  Yehuda Lindell,et al.  Introduction to Modern Cryptography , 2004 .

[8]  D. H. Rao,et al.  Pseudo random number generator using Elman neural network , 2011, 2011 IEEE Recent Advances in Intelligent Computational Systems.

[9]  Guanrong Chen,et al.  A Chaotic-Neural-Network-Based Encryption Algorithm for JPEG2000 Encoded Images , 2004, ISNN.

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Rafael Misoczki,et al.  The Computer for the 21st Century: Security & Privacy Challenges after 25 Years , 2017, 2017 26th International Conference on Computer Communication and Networks (ICCCN).

[12]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[13]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[14]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[17]  Yang Xiao,et al.  Security and Privacy in Smart Grids , 2013 .

[18]  Jinde Cao,et al.  Cryptography based on delayed chaotic neural networks , 2006 .

[19]  Chengqing Li,et al.  Cryptanalyses of Some Multimedia Encryption Schemes , 2006, IACR Cryptol. ePrint Arch..

[20]  Yakup Kutlu,et al.  Improving Pseudo random number generator using artificial neural networks , 2013, 2013 21st Signal Processing and Communications Applications Conference (SIU).

[21]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[22]  Martín Abadi,et al.  Learning to Protect Communications with Adversarial Neural Cryptography , 2016, ArXiv.

[23]  Yu Zhang,et al.  Breaking a chaotic image encryption algorithm based on perceptron model , 2011, Nonlinear Dynamics.

[24]  Xing-yuan Wang,et al.  A chaotic image encryption algorithm based on perceptron model , 2010 .