Learning to Decipher from Pixels -- A Case Study of Copiale

TL;DR

This paper presents an end-to-end, transcription-free method for deciphering historical encrypted manuscripts directly from handwritten cipher images to plaintext, demonstrated on the Copiale cipher.

Contribution

It introduces the first dataset pairing cipher images with plaintext and shows that pretraining on handwriting data enhances decipherment accuracy.

Findings

Pretraining on handwriting data improves accuracy.

Transcription-free approach is feasible and effective.

Scalable alternative to traditional decipherment pipelines.

Abstract

Historical encrypted manuscripts require both paleographic interpretation of cipher symbols and cryptanalytic recovery of plaintext. Most existing computational workflows rely on a transcription-first paradigm, in which handwritten symbols are transcribed prior to decipherment. This intermediate step is labor-intensive, error-prone, and not always aligned with the goal of direct plaintext recovery. We propose an end-to-end, transcription-free approach that directly maps handwritten cipher images to plaintext. Using the Copiale cipher as a case study, we introduce the first text-line-level dataset pairing cipher images with German plaintext. We show that pretraining on generic handwriting data followed by cipher-specific fine-tuning substantially improves decipherment accuracy. Our results demonstrate that transcription-free image-to-plaintext decipherment is both feasible and effective for historical substitution ciphers, offering a simplified and scalable alternative to traditional pipelines. https://github.com/leitro/Decipher-from-Pixels-Copiale