Decipherment of Historical Manuscript Images

Abstract

European libraries and archives are filled with enciphered manuscripts from the early modern period. These include military and diplomatic correspondence, records of secret societies, private letters, and so on. Although they are enciphered with classical cryptographic algorithms, their contents are unavailable to working historians. We therefore attack the problem of automatically converting cipher manuscript images into plaintext. We develop unsupervised models for character segmentation, character-image clustering, and decipherment of cluster sequences. We experiment with both pipelined and joint models, and we give empirical results for multiple ciphers.

Decryption of historical manuscripts: the DECRYPT project

“…Since transcription and deciphering are usually separated subsequent tasks, errors in transcription are propagated, affecting heavily the decryption. Therefore, we investigate the integration of image processing and automatic decryption into one single step (as was proposed for the first time by Kevin Knight and presented in a pilot study (Yin et al 2019)) or into an iterated pipeline (feedback). This joint architecture will hopefully fasten the time-consuming transcription, minimize the errors and create synergy effects as both image processing and automatic decryption tools rely on statistical language models and clustering of symbols, which could be commonly used.…”

Compositionality of Complex Graphemes in the Undeciphered Proto-Elamite Script using Image and Text Embedding Models

“…In our data, it is not known which signs are truly related to one another, thus we refrain from giving the model explicit information about compositionality. Yin et al (2019) segment and transcribe undeciphered scripts based on visual similarities between glyphs. Although their transcription error rate is high, they still achieve partial decipherments with no human intervention.…”

Can Sequence-to-Sequence Models Crack Substitution Ciphers?

“…This noise can come from the natural degradation of historical documents, human mistakes during a manual transcription process, or misspelled words by the author, as in the Zodiac-408 cipher. Noise can also come from automatically transcribing historical ciphers using Optical Character Recognition (OCR) techniques (Yin et al, 2019). It is thus crucial to have a robust decipherment model that can still crack ciphers despite the noise.…”

“…Hauer et al (2014) test their proposed method on noisy ciphers created by randomly corrupting log 2 (N ) of the ciphertext characters. However, automatic transcription of historical documents is very challenging and can introduce more types of noise, including the addition and deletion of some characters during character segmentation (Yin et al, 2019). We test our model on three types of random noise: insertion, deletion, and substitution.…”