Theoretical Explanation and Improvement of Deep Learning-aided Cryptanalysis

ePrint Report: Theoretical Explanation and Improvement of Deep Learning-aided Cryptanalysis

Weixi Zheng, Liu Zhang, Zilong Wang

At CRYPTO 2019, Gohr demonstrated that differential-neural distinguishers (DNDs) for Speck32/64 can learn more features than classical cryptanalysis's differential distribution tables (DDT). Furthermore, a non-classical key recovery procedure is devised by combining the Upper Confidence Bound (UCB) strategy and the BayesianKeySearch algorithm. Consequently, the time complexity of 11-round key recovery attacks on Speck32/64 is significantly reduced compared with the state-of-the-art results in classical cryptanalysis. …

can cryptanalysis crypto deep learning distribution eprint report features improvement key learn non procedure recovery report tables wang