2022/03/07 by Yi Chen, Yantian Shen, Haiyan Yu +2 · 5 citations
Computer Science · Social Sciences · #Algorithm #Chaos-based Image/Signal Encryption #Ciphertext #Computer science #Computer security #Cryptographic Implementations and Security #Encryption #Intelligence, Security, War Strategy
paper · pdf · doi:10.1093/comjnl/bxac019
published in The Computer Journal 66(6), 1419-1433 (Oxford University Press)
openalex created_date 2021/10/11 · openalex publication_date 2022/03/07 · openalex updated_date 2026/06/18
Abstract Neural-aided cryptanalysis is a challenging topic, in which the neural distinguisher (ND) is a core module. In this paper, we propose a new ND considering multiple ciphertext pairs simultaneously. Besides, multiple ciphertext pairs are constructed from different keys. The motivation is that the distinguishing accuracy can be improved by exploiting features derived from multiple ciphertext pairs. To verify this motivation, we have applied this new ND to five different ciphers. Experiments show that taking multiple ciphertext pairs as input indeed brings accuracy improvement. Then, we prove that our new ND applies to two different neural-aided key recovery attacks. Moreover, the accuracy improvement is helpful for reducing the data complexity of the neural-aided statistic attack. The code is available at https://github.com/AI-Lab-Y/NDmc.