An improved integral distinguisher scheme based on neural networks

Zahednejad, Behnam; Lyu, Lijun

doi:10.1002/int.22895

Cited by 4 publications

(2 citation statements)

References 61 publications

(143 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With regards to the cryptanalysis of Speck and Simon, other works followed. Zahednejhad et al [25] applied the DL methodology proposed by Gohr to construct a neural-based integral distinguisher scheme for several block ciphers, including Speck32, Present, RECT-ANGLE, and LBlock. The neural-based integral distinguisher increased the number of distinguished rounds of most block ciphers by at least one round, when compared to the state-of-the-art integral distinguishing method.…”

Section: Previous Workmentioning

confidence: 99%

On Pseudorandomness and Deep Learning: A Case Study

2023

View full text Add to dashboard Cite

Pseudorandomness is a crucial property that the designers of cryptographic primitives aim to achieve. It is also a key requirement in the calls for proposals of new primitives, as in the case of block ciphers. Therefore, the assessment of the property is an important issue to deal with. Currently, an interesting research line is the understanding of how powerful machine learning methods are in distinguishing pseudorandom objects from truly random objects. Moving along such a research line, in this paper a deep learning-based pseudorandom distinguisher is developed and trained for two well-known lightweight ciphers, Speck and Simon. Specifically, the distinguisher exploits a convolutional Siamese network for distinguishing the outputs of these ciphers from random sequences. Experiments with different instances of Speck and Simon show that the proposed distinguisher highly able to distinguish between the two types of sequences, with an average accuracy of 99.5% for Speck and 99.6% for Simon. Hence, the proposed method could significantly impact the security of these cryptographic primitives and of the applications in which they are used.

show abstract

Section: Previous Workmentioning

confidence: 99%

On Pseudorandomness and Deep Learning: A Case Study

2023

View full text Add to dashboard Cite

show abstract

“…The findings show that in the DES cipher, a neural network can distinguish the XOR distribution of a linear expression. Other attacks, such as integral, have also been studied in connection with machine learning [6].…”

Section: Related Work Of Use Machine Learning In Cryptanalysismentioning

confidence: 99%

Automated Deep Learning BLACK-BOX Attack for Multimedia P-BOX Security Assessment

et al. 2022

View full text Add to dashboard Cite

Resistance to differential cryptanalysis is a fundamental security requirement for symmetric block ciphers, and recently, deep learning has attracted the interest of cryptography experts, particularly in the field of block cipher cryptanalysis, where the bulk of these studies are differential distinguisher based black-box attacks. This paper provides a deep learning-based decryptor technique for investigating the permutation primitives used in multimedia block cipher encryption algorithms.We aim to investigate how deep learning can be used to improve on previous classical works by employing cipher text pair aspects to maximize information extraction with low-data constraints by using convolution neural network features to discover the correlation among permutable atoms to extract the plain text from the ciphered text without any P-box expertise. The evaluation of testing methods has been conceptualized as a regression task in which neural networks are supervised using a variety of parameters such as variations between input and output, number of iterations, and P-box generation patterns. On the other hand, the transfer learning skills demonstrated in this study indicate that discovering suitable testing models from the ground is also achievable using our model with optimum prior cryptographic expertise, where we contribute the results of deep learning in the field of deep learning based differential cryptanalysis development.Various experiments were performed on discrete and continuous chaotic and non-chaotic permutation patterns, and the best-performing model had an MSE of 1.8217e −04 and an R 2 of 1, demonstrating the practicality of the suggested technique.

show abstract

Investigating and Enhancing the Neural Distinguisher for Differential Cryptanalysis

WANG,

SUN

2024

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

At Crypto 2019, Gohr first adopted the neural distinguisher for differential cryptanalysis, and since then, this work received increasing attention. However, most of the existing work focuses on improving and applying the neural distinguisher, the studies delving into the intrinsic principles of neural distinguishers are finite. At Eurocrypt 2021, Benamira et al. conducted a study on Gohr's neural distinguisher. But for the neural distinguishers proposed later, such as the r-round neural distinguishers trained with k ciphertext pairs or ciphertext differences, denoted as N D c p k_r (Gohr's neural distinguisher is the special N D c p k_r with k = 1) and N D c d k_r , such research is lacking. In this work, we devote ourselves to study the intrinsic principles and relationship between N D c d k_r and N D c p k_r . Firstly, we explore the working principle of N D c d 1_r through a series of experiments and find that it strongly relies on the probability distribution of ciphertext differences. Its operational mechanism bears a strong resemblance to that of N D c p 1_r given by Benamira et al.. Therefore, we further compare them from the perspective of differential cryptanalysis and sample features, demonstrating the superior performance of N D c p1_r can be attributed to the relationships between certain ciphertext bits, especially the significant bits. We then extend our investigation to N D c p k_r , and show that its ability to recognize samples heavily relies on the average differential probability of k ciphertext pairs and some relationships in the ciphertext itself, but the reliance between k ciphertext pairs is very weak. Finally, in light of the findings of our research, we introduce a strategy to enhance the accuracy of the neural distinguisher by using a fixed difference to generate the negative samples instead of the random one. Through the implementation of this approach, we manage to improve the accuracy of the neural distinguishers by approximately 2% to 8% for 7-round Speck32/64 and 9-round Simon32/64.

show abstract

An improved integral distinguisher scheme based on neural networks

Cited by 4 publications

References 61 publications

On Pseudorandomness and Deep Learning: A Case Study

On Pseudorandomness and Deep Learning: A Case Study

Automated Deep Learning BLACK-BOX Attack for Multimedia P-BOX Security Assessment

Investigating and Enhancing the Neural Distinguisher for Differential Cryptanalysis

Contact Info

Product

Resources

About