Conditional differential analysis on the KATAN ciphers based on deep learning

Abstract

Abstract KATAN ciphers are block ciphers using non‐linear feedback shift registers. In this study, the authors improve the results of conditional differential analysis on KATAN by using deep learning. Multi‐differential neural distinguishers are built to improve the accuracy of the neural distinguishers and increase the number of its rounds. Moreover, a conditional differential analysis framework is proposed based on deep learning with the multi‐differential neural distinguishers, resulting in a significant improvement than the previous. We present a practical key recovery attack on the 97‐round KATAN32 with 215.5 data complexity and 220.5 time complexity. The attack of the 82‐round KATAN48 and 70‐round KATAN64 are also presented as the best known practical results.

Keywords

• block cipher
• conditional differential analysis
• deep learning
• KATAN family
• neural network