A Block Cipher Algorithm Identification Scheme Based on Hybrid Random Forest and Logistic Regression Model

Yuan, Ke; Huang, Yabing; Li, Jiabao; Jia, Chunfu; Yu, Daoming

doi:10.1007/s11063-022-11005-2

Cited by 7 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this research, the cryptograms of the AES and Blowfish algorithms in ECB encryption mode were submitted to the fifteen component tests of the NIST SP 800-22rev1a suite. The results obtained here are significantly superior to those obtained by YUAN, Ke et al in [34] and [35], where ciphertext files of 1, 8, 64, 256 and 512 KB were submitted to ten tests contained in this test battery. Special attention must be paid to the KNN classifier, which showed total accuracy in samples of 60KB.…”

Section: Results and Performance Analysiscontrasting

confidence: 61%

Post-quantum cryptographic algorithm identification using machine learning

Rocha

Xexeo

Torres

2022

J. Inf. Secur. Cryptogr.

View full text Add to dashboard Cite

This research presents a study on the identification of post-quantum cryptography algorithms through machine learning techniques. Plain text files were encoded by four post-quantum algorithms, participating in NIST's post-quantum cryptography standardization contest, in ECB mode. The resulting cryptograms were submitted to the NIST Statistical Test Suite to enable the creation of metadata files. These files provide information for six data mining algorithms to identify the cryptographic algorithm used for encryption. Identification performance was evaluated in samples of different sizes. The successful identification of each machine learning algorithm is higher than a probabilistic bid, with hit rates ranging between 73 and 100%.

show abstract

Section: Results and Performance Analysiscontrasting

confidence: 61%

Post-quantum cryptographic algorithm identification using machine learning

Rocha

Xexeo

Torres

2022

J. Inf. Secur. Cryptogr.

View full text Add to dashboard Cite

show abstract

“…Features were extracted from ciphertext files of 1KB, 8KB, 64KB, 256KB, and 512KB through the NIST randomness test method and entropy test method, and then the multi-layer perceptron model was used to group the five types of AES, 3DES, Blowfish, CAST and RC2 the cryptographic algorithm performs single-layer recognition, and finally compared with five traditional machine learning algorithms, it is found that the single-layer recognition scheme of the cryptographic algorithm based on the multi-layer perceptron model has a higher recognition rate and better stability. In 2023, Yuan et al [12] based on the existing identification scheme, a new cluster division scheme CMSSBAM-cluster is proposed, and then a multi-layer composite identification scheme using a composite structure cryptographic algorithm was proposed. This scheme uses cluster division and single division methods to identify various cryptographic algorithms.…”

Section: Introductionmentioning

confidence: 99%

A Block Cipher Recognition Scheme Based on Deep Learning Transformer Algorithm

Yuan,

Zhang,

Zhou

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Cryptographic algorithms are the core of data encryption, and their identification is a prerequisite for in-depth analysis of cryptography. Cryptographic algorithm identification is the process of distinguishing or identifying encryption methods by analyzing potentially distinctive information in the ciphertext when the ciphertext is known. It serves as the foundation for cryptanalysis work. The machine learning-based approach for identifying cryptographic algorithms extracts ciphertext features and trains the machine learning algorithm to build a cryptographic system identification classifier. It has the characteristics of high accuracy, concise operation process, and strong practicability. The ciphertext's complexity and the inter-data interference both rise with the number of cryptographic algorithms. This will lead to a reduction in the recognition rate of traditional machine learning cryptographic algorithm recognition solutions, poor recognition stability, and huge challenges to recognition capabilities. Deep learning algorithms have the characteristics of strong learning ability, a large amount of data processing, wide-coverage, good adaptability, and portability, etc., and have become a hot spot in the realm of cryptographic algorithm identification. In this work, a cryptographic algorithm identification methodology based on the Transformer algorithm is proposed, and the ciphertext feature extraction approach in the NIST randomness test is improved. In the research on cryptographic algorithm identification, we selected five block cipher algorithms: AES, 3DES, Blowfish, CAST, and RC2 as the research objects, and conducted two-class and five-class recognition experiments. According to experimental data, the approach suggested in this article has superior accuracy and stability than the classic machine learning model when the ciphertext size and other experimental variables are the same. Among them, on ciphertext files ranging from 1kb to 512kb, compared to the accuracy of the conventional classic machine learning algorithms SVM, GNB, KNN, RF, and LR, the average recognition accuracy of the two categories is 0.855, which is 29% higher. 33.9%, 28.5%, 34.2%, and 29.9%. Compared with the MLP accuracy of the same deep learning algorithm, the accuracy is also improved by 9%. When conducting the five-category experiment, the recognition accuracy of the scheme put forward in this piece is not less than 0.4. When the ciphertext file is 512KB, the recognition accuracy is as high as 0.42, and the average recognition accuracy of the five categories is 0.412. It is far greater than the other five classic machine learning algorithms and significantly better than the 20% random classification accuracy. Other algorithms' recognition rates fluctuate as ciphertext file sizes change. Among them, the Transformer algorithm has the smallest fluctuation and the best overall effect.

show abstract

“…The experimental results demonstrate that the model is unable to recognize the method efficiently because it is difficult to acquire the necessary details of the ciphertext algorithm. Yuan et al [12] designed a Hybrid Gradient Boosting Decision Tree and a logistic regression model, which reduced the impact of ciphertext length on recognition accuracy and strengthened the stability of the model. However, the accuracy of multi-classification has not improved and the five-classification accuracy is only about 30%.…”

Section: Introductionmentioning

confidence: 99%

Block Cipher Identification Scheme Based on Hamming Weight Distribution

Zhao

Chi

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In order to solve the problem of worse recognition performance under the multi-classification scenarios of existing cryptosystem identification, this paper proposes a block cryptosystem recognition scheme based on Hamming weight distribution. A feature extraction method based on Hamming weight distribution is designed to extract the cipher text features, and the cryptosystem is further described. XGBoost-RFE feature selection algorithm is proposed to filter invalid features. In order to better adapt to the characteristics of complex ciphertext data and difficult fitting in multi classification scenarios, XGB-LGBM ensemble learning model with multi-layer fusion structure is designed to further improve the accuracy and generalization of recognition. The experiment carried out mixed identification of 10 common block cipher algorithm, and the overall recognition accuracy reached 89.65%.

show abstract

A Block Cipher Algorithm Identification Scheme Based on Hybrid Random Forest and Logistic Regression Model

Cited by 7 publications

References 19 publications

Post-quantum cryptographic algorithm identification using machine learning

Post-quantum cryptographic algorithm identification using machine learning

A Block Cipher Recognition Scheme Based on Deep Learning Transformer Algorithm

Block Cipher Identification Scheme Based on Hamming Weight Distribution

Contact Info

Product

Resources

About