On possibility of using convolutional neural networks for creating universal attacks on iterative block~ciphers

A. A. Perov ; A. I. Pestunov

Prikladnaâ diskretnaâ matematika, no. 3 (2020), pp. 46-56.

Résumé

The paper explores possibility of applying convolutional neural networks to the security analysis of iterative block ciphers. A new approach for constructing distinguishing attacks based on a convolutional neural network is proposed. The approach is based on distinguishing between graphic equivalents of ciphertexts received by the CTR (counter) encryption mode after different number of rounds, including the number of rounds guaranteeing satisfaction of statistical properties. Several schemes are presented for constructing distinguishing attacks, which in some cases make it possible to detect deviations from randomness in smaller samples than previously known, and with a large number of rounds. The approach allows to create distinguishers without the need for an analytical research of each cipher, which makes it possible to build universal distinguishers for a series of ciphers.

Détail

Keywords: block cipher, machine learning, neural network, statistical analysis, distinguishing attack
Mots-clés : cryptanalysis.

Bibliographie

[1] Biham E., Shamir A., “Differential cryptanalysis of DES-like cryptosystems”, J. Cryptology, 4 (1991), 3–72 | DOI | MR | Zbl

[2] Knudsen L., “Truncated and higher order differentials”, LNCS, 1008, 1994, 196–211

[3] Biham E., Biryukov A., Shamir A., “Cryptanalysis of Skipjack reduced to 31 rounds using impossible differentials”, J. Cryptology, 18 (2005), 291–311 | DOI | MR | Zbl

[4] Matsui M., “Linear cryptanalysis method for DES cipher”, LNCS, 765, 1994, 386–397 | Zbl

[5] Knudsen L., “Integral cryptanalysis”, LNCS, 2365, 2002, 112–127 | Zbl

[6] Biryukov A., Shamir A., “Structural cryptanalysis of SASAS”, J. Cryptology, 23 (2010), 505–518 | DOI | MR | Zbl

[7] Agibalov G. P., “Some theoretical aspects of differential cryptanalysis of the iterated block ciphers with additive round key”, Prikladnaya Diskretnaya Matematika, 2008, no. 1(1), 34–42 (in Russian) | Zbl

[8] Denisov O. V., “Markov criteria for block cipher algorithms”, Prikladnaya Diskretnaya Matematika, 2018, no. 41, 28–37 (in Russian)

[9] Denisov O. V., Bylina R. A., “Matrix formula for the spectrum of output distribution of block cipher scheme and statistical criterion based on this formula”, Prikladnaya Diskretnaya Matematika, 2016, no. 2(32), 33–48 (in Russian)

[10] Tokareva N. N., “About quadratic approximations in block ciphers”, Problemy Peredachi Informacii, 3 (2008), 105–127 (in Russian) | Zbl

[11] Agibalov G. P., “Substitution block ciphers with functional keys”, Prikladnaya Diskretnaya Matematika, 2017, no. 38, 57–65 | MR

[12] Soskov A. S., Ryabko B. Ya., “Applying distinction attack on lightweight block ciphers based on ARX operations”, Vychislitel'nye Tekhnologii, 3 (2019), 106–116 (in Russian)

[13] Pestunov A. I., “Statistical analysis of modern block ciphers”, Vychislitel'nye Tekhnologii, 12:2 (2007), 122–129 (in Russian) | Zbl

[14] Knudsen L., Meier W., “Correlations in RC6 with a reduced number of rounds”, LNCS, 1978, 2001, 94–108 | Zbl

[15] Ryabko B. Ya., Stognienko V. S., SHokin Yu. I., “Adaptive Chi-square test for distinguishing close hypotheses with a large number of classes and its application to some cryptography problems”, Problemy Peredachi Informacii, 39:2 (2003), 53–62 (in Russian) | MR | Zbl

[16] Monarev V. A., Ryabko B. Ya., “Experimental analysis of pseudo-random number generators using a new statistical test”, Zhurnal Vychislitel'noj Matematiki i Matematicheskoj Fiziki, 44:5 (2004), 766–770 (in Russian) | MR | Zbl

[17] Ryabko B. Ya., Pestunov A. I., “Book Stack as a new statistical test for random numbers”, Problemy Peredachi Informacii, 40:1 (2004), 73–78 (in Russian) | MR | Zbl

[18] Ryabko B. Ya., Monarev V. A., Shokin Yu. I., “A new type of attack on block ciphers”, Problemy Peredachi Informacii, 41:4 (2005), 97–107 (in Russian) | MR | Zbl

[19] Monarev V. A., “Implementation of a new statistical attack on a block cipher”, Vestnik SibGUTI, 1 (2014), 85–90 (in Russian)

[20] Lysyak A. S., Ryabko B. Ya., Fionov A. N., “Analysis of the effectiveness of gradient statistical attacks on block ciphers RC6, MARS, CAST-128, IDEA, Blowfish in information security systems”, Vestnik SibGUTI, 2013, no. 1, 85–109 (in Russian)

[21] Lerman L., Bontempi G., Markowitch O., “A machine learning approach against a masked AES”, J. Cryptogr. Eng., 5 (2015), 123–139 | DOI | MR

[22] Hettwer B., Gehrer S., Guneysu T., “Applications of machine learning techniques in side-channel attacks: a survey”, J. Cryptogr. Eng., 10 (2020), 135–162 | DOI

[23] Szegedy C., Vanhoucke V., Ioffe S., et al., “Rethinking the inception architecture for computer vision”, Proc. IEEE Conf. CVPR (Las Vegas, NV, USA, June 27–30, 2016), 2818–2826

[24] Monarev V. A., Pestunov A. I., “Efficient steganography detection by means of compression-based integral classifier”, Prikladnaya Diskretnaya Matematika, 2018, no. 40, 59–71 (in Russian) | MR

[25] Monarev V. A., Pestunov A. I., “Enhancing steganalysis accuracy via tentative filtering of stego-containers”, Prikladnaya Diskretnaya Matematika, 2016, no. 2(32), 87–99 (in Russian) | MR

[26] Kodovsky J., Fridrich J., Holub V., “Ensemble classifiers for steganalysis of digital media”, IEEE Trans. Inform. Forensics and Security, 7:2 (2010), 434–444 | MR

[27] Pestunov A. I., Perov A. A., “Software library for statistical analysis of iterative block ciphers”, Informacionnoe Protivodejstvie Ugrozam Terrorizma, 24 (2015), 197–202 (in Russian)