Can Sequence-to-Sequence Models Crack Substitution Ciphers?

TL;DR

This paper introduces an end-to-end multilingual sequence-to-sequence model capable of deciphering simple substitution ciphers from both synthetic and real historical data, without needing prior language identification.

Contribution

The paper presents a novel end-to-end neural model that can decipher substitution ciphers across multiple languages without explicit language detection, handling noisy and historical texts.

Findings

Effective on synthetic and real ciphers

No need for language identification

Robust to noise in ciphertexts

Abstract

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.