Volume 7, Issue 4 (April 2020), Pages: 29-38

----------------------------------------------

 Original Research Paper

 Title: A new neural-network-based model for measuring the strength of a pseudorandom binary sequence

 Author(s): Ahmed Alamer ^{1, 2,} *, Ben Soh ¹

 Affiliation(s):

 ¹Department of Computer Science and Information Technology, School of Engineering and Mathematical Sciences, La Trobe University, Bundoora, Australia
 ²Department of Mathematics, College of Science, Tabuk University, Tabuk, Saudi Arabia

  Full Text - PDF          XML

 * Corresponding Author. 

  Corresponding author's ORCID profile: https://orcid.org/0000-0002-1249-6424

 Digital Object Identifier: 

 https://doi.org/10.21833/ijaas.2020.04.005

 Abstract:

Maximum order complexity is an important tool for measuring the nonlinearity of a pseudorandom sequence. There is a lack of tools for predicting the strength of a pseudorandom binary sequence in an effective and efficient manner. To this end, this paper proposes a neural network (NN) based model for measuring the strength of a pseudorandom binary sequence. Using the shrinking generator (SG) keystream as pseudorandom binary sequences and then calculating the unique window size (UWS) as a representation of maximum order complexity, we can demonstrate that the proposed model provides more accurate and efficient measurements than the classical method for predicting maximum order complexity. By using UWS, which is a method of pseudorandomness measurement, we can identify with higher accuracy the level of pseudorandomness of given binary sequences. As there are different randomness tests and predicting methods, we present a prediction model that has high accuracy in comparison with current methods. This method can be used to evaluate the ciphers’ pseudorandom number generator (PRNG) and can also be used to evaluate the internal components by investigating their binary output sequence pseudorandomness. Our aim is to provide an application for NN pseudorandomness and in cryptanalysis in general, as well as demonstrating the models’ mathematical description and implementations. Therefore, applying NN models to predict UWS utilizes two layers of pseudorandomness testing of binary sequences and is an essential cryptanalysis tool that can be extended to other fields such as pattern recognition. 

 © 2020 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords: Neural network, Binary sequence, Pseudorandomness, Stream cipher, Shrinking generator, Randomness testing

 Article History: Received 18 October 2019, Received in revised form 17 January 2020, Accepted 17 January 2020

 Acknowledgment:

We would like to thank “Lito P. Cruz” for the valuable Neural Network comments.

 Compliance with ethical standards

 Conflict of interest: The authors declare that they have no conflict of interest.

 Citation:

 Alamer A and Soh B (2020). A new neural-network-based model for measuring the strength of a pseudorandom binary sequence. International Journal of Advanced and Applied Sciences, 7(4): 29-38

 Permanent Link to this page

 Figures

 No Figure

 Tables

 Table 1 Table 2 Table 3 Table 4 Table 5 Table 6 

----------------------------------------------

 References (42) 

1. Allam AM and Abbas HM (2011). Group key exchange using neural cryptography with binary trees. In the 24^th Canadian Conference on Electrical and Computer Engineering, IEEE, Niagara Falls, Canada: 000783-000786. https://doi.org/10.1109/CCECE.2011.6030562   [Google Scholar]
2. Bishop CM (2006). Pattern recognition and machine learning. Springer-Verlag, New York, USA.   [Google Scholar]
3. Boztas S and Alamer A (2015). Statistical dependencies in the Self-Shrinking Generator. In the Seventh International Workshop on Signal Design and its Applications in Communications, IEEE, Bengaluru, India: 42-46. https://doi.org/10.1109/IWSDA.2015.7458410   [Google Scholar]
4. Brandstätter N and Winterhof A (2006). Linear complexity profile of binary sequences with small correlation measure. Periodica Mathematica Hungarica, 52(2): 1-8. https://doi.org/10.1007/s10998-006-0008-1   [Google Scholar]
5. Chen ST, Yu DC, and Moghaddamjo AR (1992). Weather sensitive short-term load forecasting using nonfully connected artificial neural network. IEEE Transactions on Power Systems, 7(3): 1098-1105. https://doi.org/10.1109/59.207323   [Google Scholar]
6. Coppersmith D, Krawczyk H, and Mansour Y (1993). The shrinking generator. In the Annual International Cryptology Conference, Springer, Santa Barbara, USA: 22-39. https://doi.org/10.1007/3-540-48329-2_3   [Google Scholar]
7. Diffie W and Hellman ME (1976). New directions in cryptography. IEEE Transactions on Information Theory, 22(6): 644–654. https://doi.org/10.1109/TIT.1976.1055638   [Google Scholar]
8. Dubrova E and Hell M (2017). Espresso: A stream cipher for 5G wireless communication systems. Cryptography and Communications, 9(2): 273-289. https://doi.org/10.1007/s12095-015-0173-2   [Google Scholar]
9. Erdmann D and Murphy S (1997). An approximate distribution for the maximum order complexity. Designs, Codes and Cryptography, 10(3): 325-339. https://doi.org/10.1023/A:1008295603824   [Google Scholar]
10. Fan F and Wang G (2018). Learning from pseudo-randomness with an artificial neural network–Does god play pseudo-dice? IEEE Access, 6: 22987-22992. https://doi.org/10.1109/ACCESS.2018.2826448   [Google Scholar]
11. Godhavari T, Alamelu NR, and Soundararajan R (2005). Cryptography using neural network. In the Annual IEEE India Conference-Indicon, IEEE, Chennai, India: 258-261. https://doi.org/10.1109/INDCON.2005.1590168   [Google Scholar]
12. Golić JD (2001). Correlation analysis of the shrinking generator. In the Annual International Cryptology Conference, Springer, Santa Barbara, USA: 440-457. https://doi.org/10.1007/3-540-44647-8_26   [Google Scholar]
13. Hagan MT, Demuth HB, Beale MH, and De Jesús O (1996). Neural network design. PWS Publisher, Boston, USA.   [Google Scholar]
14. Hell M and Johansson T (2006). Two new attacks on the self-shrinking generator. IEEE Transactions on Information Theory, 52(8): 3837-3843. https://doi.org/10.1109/TIT.2006.878233   [Google Scholar]
15. Hertz J, Krogh A, and Palmer RG (1991). Introduction to the theory of neural computation. Addison Wesley Longman Publishing, Boston, USA. https://doi.org/10.1063/1.2810360   [Google Scholar]
16. Jansen CJ (1991). The maximum order complexity of sequence ensembles. In the Workshop on the Theory and Application of Cryptographic Techniques, Springer, Brighton, UK: 153-159. https://doi.org/10.1007/3-540-46416-6_13   [Google Scholar]
17. Jansen CJA (1989). Investigations on nonlinear streamcipher systems: Construction and evaluation methods. Ph.D. Dissertation, Technical University of Delft, Delft, Netherlands.   [Google Scholar]
18. Johansson T (1998). Reduced complexity correlation attacks on two clock-controlled generators. In the International Conference on the Theory and Application of Cryptology and Information Security, Springer, Beijing, China: 342-356. https://doi.org/10.1007/3-540-49649-1_27   [Google Scholar]
19. Keras (2019). Keras: The python deep learning library. Available online at: https://bit.ly/32k8qYV
20. Khan J, Wei JS, Ringner M, Saal LH, Ladanyi M, Westermann F, and Meltzer PS (2001). Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nature Medicine, 7(6): 673-679. https://doi.org/10.1038/89044   [Google Scholar] PMid:11385503 PMCid:PMC1282521
21. Kimoto T, Asakawa K, Yoda M, and Takeoka M (1990). Stock market prediction system with modular neural networks. In the IJCNN International Joint Conference on Neural Networks, IEEE, San Diego, USA: 1-6. https://doi.org/10.1109/IJCNN.1990.137535   [Google Scholar]
22. Kinzel W and Kanter I (2002). Interacting neural networks and cryptography. In: Kramer B (Ed.), Advances in solid state physics: 383-391. Springer, Berlin, Germany. https://doi.org/10.1007/3-540-45618-X_30   [Google Scholar]
23. Li P, Li J, Huang Z, Li T, Gao CZ, Yiu SM, and Chen K (2017). Multi-key privacy-preserving deep learning in cloud computing. Future Generation Computer Systems, 74: 76-85. https://doi.org/10.1016/j.future.2017.02.006   [Google Scholar]
24. Liang H, Chen W, and Tang Y (2017). A class of binary cyclic codes and sequence families. Journal of Applied Mathematics and Computing, 53(1-2): 733-746. https://doi.org/10.1007/s12190-016-0993-z   [Google Scholar]
25. Liu J and Mesnager S (2019). Weightwise perfectly balanced functions with high weight wise nonlinearity profile. Designs, Codes and Cryptography, 87(8): 1797-1813. https://doi.org/10.1007/s10623-018-0579-x   [Google Scholar]
26. Meidl W and Niederreiter H (2016). Multisequences with high joint nonlinear complexity. Designs, Codes and Cryptography, 81(2): 337-346. https://doi.org/10.1007/s10623-015-0142-y   [Google Scholar]
27. Meier W and Staffelbach O (1994). The self-shrinking generator. In: Blahut RE, Costello DJ, Maurer U, and Mittelholzer T (Eds.), Communications and cryptography: 287-295. Springer, Boston, USA. https://doi.org/10.1007/978-1-4615-2694-0_28   [Google Scholar] PMid:8203104
28. Mérai L and Winterhof A (2018). On the pseudorandomness of automatic sequences. Cryptography and Communications, 10(6): 1013-1022. https://doi.org/10.1007/s12095-017-0260-7   [Google Scholar]
29. Mérai L, Niederreiter H, and Winterhof A (2017). Expansion complexity and linear complexity of sequences over finite fields. Cryptography and Communications, 9(4): 501-509. https://doi.org/10.1007/s12095-016-0189-2   [Google Scholar]
30. Mihaljević MJ (1996). A faster cryptanalysis of the self-shrinking generator. In the Australasian Conference on Information Security and Privacy, Springer, Wollongong, Australia: 182-189. https://doi.org/10.1007/BFb0023298   [Google Scholar]
31. Ritter T (1991). The efficient generation of cryptographic confusion sequences. Cryptologia, 15(2): 81-139. https://doi.org/10.1080/0161-119191865812   [Google Scholar]
32. Su J, Vargas DV, and Sakurai K (2019). One pixel attack for fooling deep neural networks. IEEE Transactions on Evolutionary Computation, 23(5): 828-841. https://doi.org/10.1109/TEVC.2019.2890858   [Google Scholar]
33. Sun Z and Winterhof A (2019). On the maximum order complexity of the Thue-Morse and Rudin-Shapiro sequence. arXiv:1910.13723v1 [math.CO]. https://doi.org/10.1080/23799927.2019.1566275   [Google Scholar]
34. Sun Z, Zeng X, Li C, and Helleseth T (2017). Investigations on periodic sequences with maximum nonlinear complexity. IEEE Transactions on Information Theory, 63(10): 6188-6198. https://doi.org/10.1109/TIT.2017.2714681   [Google Scholar]
35. Tang D and Liu J (2019). A family of weight wise (almost) perfectly balanced Boolean functions with optimal algebraic immunity. Cryptography and Communications, 11: 1185-1197. https://doi.org/10.1007/s12095-019-00374-6   [Google Scholar]
36. TensorFlow (2019). An open source machine learning framework. Available online at: https://bit.ly/3c3YSWs
37. Turan MS (2012). On the nonlinearity of maximum-length NFSR feedbacks. Cryptography and Communications, 4(3-4): 233-243. https://doi.org/10.1007/s12095-012-0067-5   [Google Scholar]
38. Uğuz M, Doğanaksoy A, Sulak F, and Koçak O (2019). R-2 composition tests: A family of statistical randomness tests for a collection of binary sequences. Cryptography and Communications, 11(5): 921-949. https://doi.org/10.1007/s12095-018-0334-1   [Google Scholar]
39. Wang Y and Nicol T (2015). On statistical distance based testing of pseudo random sequences and experiments with PHP and Debian OpenSSL. Computers and Security, 53: 44-64. https://doi.org/10.1016/j.cose.2015.05.005   [Google Scholar]
40. Xiao Z, Zeng X, Li C, and Jiang Y (2019). Binary sequences with period N and nonlinear complexity N−2. Cryptography and Communications, 11(4): 735-757. https://doi.org/10.1007/s12095-018-0324-3   [Google Scholar]
41. Zatorre RJ, Chen JL, and Penhune VB (2007). When the brain plays music: Auditory–motor interactions in music perception and production. Nature Reviews Neuroscience, 8(7): 547-558. https://doi.org/10.1038/nrn2152   [Google Scholar] PMid:17585307
42. Zoufal C, Lucchi A, and Woerner S (2019). Quantum generative adversarial networks for learning and loading random distributions. npj Quantum Information, 5(1): 1-9. https://doi.org/10.1038/s41534-019-0223-2   [Google Scholar]