PIPO 64/128에 대한 딥러닝 기반의 신경망 구별자
Deep Learning-Based Neural Distinguisher for PIPO 64/128
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
차분 분석은 블록 암호에 대한 분석 기법 중 하나이며, 입력 차분에 대한 출력 차분이 높은 확률로 존재한다는 성질을 이용한다. 무작위 데이터와 특정 출력 차분을 갖는 데이터를 구별할 수 있다면, 차분분석에 대한 데이터 복잡도를 감소시킬 수 있다. 이를 위해 딥러닝 기반의 신경망 구별자에 대한 연구들이 다수 진행되었으며, 본 논문에서는 PIPO 64/128에 대한 최초의 딥러닝 기반의 신경망 구별자를 제안하였다. 여러 입력 차분들을 사용하여 실험한 결과, 0, 1, 3, 5-라운드의 차분 특성에 대한 3 라운드 신경망 구별자가 각각 0.71, 0.64, 0.62, 0.64의 정확도를 달성하였다. 이 구별자는 고전 구별자와 함께 사용될 경우 최대 8 라운드에 대한 구별 공격이 가능하도록 한다. 따라서 여러 라운드의 입력 차분을 처리할 수 있는 구별자를 찾아냄으로써 확장성을 확보하였다. 향후에는 성능 향상을 위한 최적의 신경망을 구성하기 위해 다양한 신경망 구조를 적용하고, 연관 키 차분을 사용하거나 다중 입력차분을 위한 신경망 구별자를 구현할 예정이다.
Abstract
Differential cryptanalysis is one of the analysis techniques for block ciphers, and uses the property that the output difference with respect to the input difference exists with a high probability. If random data and differential data can be distinguished, data complexity for differential cryptanalysis can be reduced. For this, many studies on deep learning-based neural distinguisher have been conducted. In this paper, a deep learning-based neural distinguisher for PIPO 64/128 is proposed. As a result of experiments with various input differences, the 3-round neural distinguisher for the differential characteristics for 0, 1, 3, and 5-rounds achieved accuracies of 0.71, 0.64, 0.62, and 0.64, respectively. This work allows distinguishing attacks for up to 8 rounds when used with the classical distinguisher. Therefore, scalability was achieved by finding a distinguisher that could handle the differential of each round. To improve performance, we plan to apply various neural network structures to construct an optimal neural network, and implement a neural distinguisher that can use related key differential or process multiple input differences simultaneously.
참고문헌 (15)
- E, "Neural networks and learning machines, 3", pp.2009, Haykin, Simon
- Gardner, Matt W., "Artificial neural networks(the multilayer perceptron)—a review of applications in the atmospheric sciences", Atmospheric environment, 32(14–15), pp.2627~2636 (1998)
- Albawi, Saad, "Understanding of a convolutional neural network", 2017 international conference on engineering and technology (ICET), pp.1~6 (2017)
- Goodfellow, Ian, "Generative adversarial networks", Communications of the ACM, 63(11), pp.139~144 (2020)
- He, Kaiming, "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- Heys, Howard M, "A tutorial on linear and differential cryptanalysis", Cryptologia, 26(3), pp.189~221 (2002)
- Gohr, Aron, "Improving attacks on round-reduced speck32", 64 using deep learning, 2019, 150~179[DOI]
- Baksi, Anubhab, "Classical and Physical Security of Symmetric Key Cryptographic Algorithms", pp.141~162 (2022), Springer
- Rajan, Reshma, "Machine Intelligence and Smart Systems", pp.397~406 (2022), Springer
- Yadav, Tarun, "Differential-ml distinguisher : Machine learning based generic extension for differential cryptanalysis", International Conference on Cryptology and Information Security in Latin America, pp.191~212 (2021), Springer
- LU, Jinyu, "Improved (Related-key) Differential-based Neural Distinguishers for SIMON and SIMECK Block Ciphers", Cryptology ePrint Archive (2023)
- Kim, Hangi, "PIPO: A lightweight block cipher with efficient higher-order masking software implementations", International Conference on Information Security and Cryptology, 12593, pp.99~122 (2021), Springer
- Yadav, Tarun, "International Conference on Security, Privacy, and Applied Cryptography Engineering", International Conference on Security, Privacy, and Applied Cryptography Engineering, 13783, pp.3~27 (2022), Springer
- Kim, Hyunji, "Deep Learning based Cryptanalysis of Lightweight Block Ciphers, Revisited", Cryptology ePrint Archive (2022)
- Bao, Zhenzhen, "Enhancing differential-neural cryptanalysis", Advances in Cryptology–ASIACRYPT 2022: 28th International Conference on the Theory and Application of Cryptology and Information Security, 13791, pp.318~347 (2023), Springer