Generic Partial Decryption as Feature Engineering for Neural Distinguishers

In Neural Cryptanalysis, a deep neural network is trained as a cryptographic distinguisher between pairs of ciphertexts (F(X), F(X )), where F is either a random permutation or a block cipher, is a fixed difference. The AutoND framework aims to use neural distinguishers that are treated as a generic tool and discourages cipher-specific optimizations. On the other hand, works such as [LLS+24] obtain superior distinguishers by adding dedicated features, such as selected parts of the difference in the previous rounds, to the input of the neural distinguishers. In this paper, we study Generic Partial Decryption as a feature engineering technique and integrate it within a fully automated pipeline, where we evaluate its effect independently of the number of pairs per sample, with which feature engineering is often combined. We show that this technique matches state-of-the-art dedicated approaches on SIMON and SIMECK. Additionally, we apply it to ARADI, and present a practical neural-assisted key recovery for 5 rounds, as well as a 7-rounds key recovery with time complexity. Additionally, we derive useful information from the neural distinguishers and propose a non-neural version of our 5-round key recovery.