BitRelation: Exploring Bit-Level Dependencies in Neural Cryptanalysis

This paper applies Explainable Artificial Intelligence (XAI) to improve the interpretability of neural differential cryptanalysis on the SPECK cipher. We use Local Interpretable Model-agnostic Explanations (LIME) to analyse and visualise feature importance in neural distinguishers, giving signed contributions and absolute rankings. Signed contributions show whether, and how strongly, specific bit positions influence the model's decision, while absolute rankings reflect their importance regardless of sign. To study interactions beyond single bits, we introduce a Systematic Masking Approach to reveal relations among bits by testing if chosen combinations of masked bits alter classification accuracy. On Gohr's 8-round SPECK32/64 distinguisher, masking up to four-bit combinations shows that decisions involve multi-bit interactions rather than isolated single-bit effects. Although LIME highlights strong single-bit signals, masking reveals interaction patterns consistent with differential cryptanalysis. These findings clarify model behaviour in neural cryptanalysis and show XAI's value for exposing and visualising interaction structure in ciphertext features and decisions.