# Can Sequence-to-Sequence Models Crack Substitution Ciphers?

arXiv: https://arxiv.org/abs/2012.15229 · HTML: https://mlsanity.com/paper/2012.15229/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [SALSA: Attacking Lattice Cryptography with Transformers](https://mlsanity.com/paper/2207.04785/) (2022)
- [Salsa Fresca: Angular Embeddings and Pre-Training for ML Attacks on Learning With Errors](https://mlsanity.com/paper/2402.01082/) (2024)
- [ICL CIPHERS: Quantifying "Learning" in In-Context Learning via Substitution Ciphers](https://mlsanity.com/paper/2504.19395/) (2025)
- [Lexinvariant Language Models](https://mlsanity.com/paper/2305.16349/) (2023)
- [Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)](https://mlsanity.com/paper/2603.01499/) (2026)
- [Segmenting Numerical Substitution Ciphers](https://mlsanity.com/paper/2205.12527/) (2022)
- [Can Transformers Break Encryption Schemes via In-Context Learning?](https://mlsanity.com/paper/2508.10235/) (2025)
- [ALICE: An Interpretable Neural Architecture for Generalization in Substitution Ciphers](https://mlsanity.com/paper/2509.07282/) (2025)
- [Joint Transcription and Decryption of Images of Encrypted Handwritten Documents: A Comparison with the Traditional Pipeline](https://mlsanity.com/paper/2606.27700/) (2026)

## Abstract (arXiv)

Decipherment of historical ciphers is a challenging problem. The language of the target plaintext might be unknown, and ciphertext can have a lot of noise. State-of-the-art decipherment methods use beam search and a neural language model to score candidate plaintext hypotheses for a given cipher, assuming the plaintext language is known. We propose an end-to-end multilingual model for solving simple substitution ciphers. We test our model on synthetic and real historical ciphers and show that our proposed method can decipher text without explicit language identification while still being robust to noise.