Advertisement

ANN Based Distinguishing Attack on RC4 Stream Cipher

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 202)

Abstract

RC4 is the most widely used stream cipher in many applications. Many Distinguishing Attacks on RC4 system have been published which are based on statistical approaches. These statistical Distinguishing Attacks exploit distribution of bytes, diagraphs and trigraphs in RC4 generated output key stream with respect to random key stream. This paper presents an Artificial Neural Network (ANN) based approach to distinguish RC4 key stream from random key stream. The Joint Mutual Information (JMI) criterion has been used in effective feature selection. The prominent features are used in Back-propagation learning of Multilayer Perceptron (MLP) network to distinguish RC4 system.

Keywords

RC4 stream cipher Distinguishing attack Joint mutual information Multilayer perceptron network Back-propagation learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Roos, A.: Class of Weak Keys in the RC4 Stream Cipher. Post in sci.crypt, (1995).Google Scholar
  2. Fluhrer, S., Mantin I. and Shamir A.: Weakness in the Key Scheduling Algorithm of RC4, LNCS 2259, 1-24, Springer Verlag (2001).Google Scholar
  3. Paul, Souradyuti and Preneel, Bart: A New Weakness in the RC4 Key-stream Generator and an Approach to Improve the Security of the Cipher, FSE-2001, 245-259, Springer Verlag (2004).Google Scholar
  4. Mantin, I.: Predicting and Distinguishing Attacks on RC4 Key-stream Generator 491-505, Springer Verlag (2005).Google Scholar
  5. Klein, Andreas: Attacks on the RC4 Stream Cipher, Journal of Design, Code and Cryptography, vol 48, issue 3, 269-286, (2008).Google Scholar
  6. Yang, H. H. and Moody, J.: Feature Selection based on Joint Mutual Information, Journal of Computational Intelligence Methods and Applications, Int. Computer Science Convention, Vol.13, 1-8, (1999).Google Scholar
  7. Brown, G., Pocock, A. and Jhao, M.J.: Conditional Likelihood Maximization: A Unifying Framework for Information Theoretic Feature Selection. Journal of Machine Learning Research, Vol.13, 27-66, (2012).Google Scholar
  8. Haykin, S.: Neural Networks- A Comprehensive Foundation, Macmillan, New York, (2001).Google Scholar
  9. Katagiri, S.: Hand Book of Neural Networks for Speech Processing, Artech House, London, 1st edition,(2000).Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  1. 1.SAG, DRDOMehrauliIndia

Personalised recommendations