Using Modular Arithmetic Optimized Neural Networks To Crack Affine Cryptographic Schemes Efficiently

TL;DR

This paper presents a hybrid neural network approach that combines modular arithmetic and statistical features to efficiently cryptanalyze affine ciphers, achieving high key recovery accuracy on short to moderate ciphertexts.

Contribution

The paper introduces a novel neural network architecture that integrates modular arithmetic processing with statistical analysis for improved cryptanalysis of affine ciphers.

Findings

High key recovery accuracy on short ciphertexts

Outperforms purely statistical methods for affine cipher

Performance decreases with very long ciphertexts

Abstract

We investigate the cryptanalysis of affine ciphers using a hybrid neural network architecture that combines modular arithmetic-aware and statistical feature-based learning. Inspired by recent advances in interpretable neural networks for modular arithmetic and neural cryptanalysis of classical ciphers, our approach integrates a modular branch that processes raw ciphertext sequences and a statistical branch that leverages letter frequency features. Experiments on datasets derived from natural English text demonstrate that the hybrid model attains high key recovery accuracy for short and moderate ciphertexts, outperforming purely statistical approaches for the affine cipher. However, performance degrades for very long ciphertexts, highlighting challenges in model generalization.