Scalable Neural Cryptanalysis of Block Ciphers in Federated Attack Environments

This paper presents an extended investigation into deep learning-based cryptanalysis of block ciphers by introducing and evaluating a multi-server attack environment. Building upon our prior work in centralized settings, we explore the practicality and scalability of deploying such attacks across multiple distributed edge servers. We assess the vulnerability of five representative block ciphers—DES, SDES, AES-128, SAES, and SPECK32/64—under two neural attack models: Encryption Emulation (EE) and Plaintext Recovery (PR), using both fully connected neural networks and Recurrent Neural Networks (RNNs) based on bidirectional Long Short-Term Memory (BiLSTM). Our experimental results show that the proposed federated learning-based cryptanalysis framework achieves performance nearly identical to that of centralized attacks, particularly for ciphers with low round complexity. Even as the number of edge servers increases to 32, the attack models maintain high accuracy in reduced-round settings. We validate our security assessments through formal statistical significance testing using two-tailed binomial tests with 99% confidence intervals. Additionally, our scalability analysis demonstrates that aggregation times remain negligible (<0.01% of total training time), confirming the computational efficiency of the federated framework. Overall, this work provides both a scalable cryptanalysis framework and valuable insights into the design of cryptographic algorithms that are resilient to distributed, deep learning-based threats.