Thousands of enciphered historical manuscripts are buried in libraries and archives. Examples of such material are diplomatic correspondence and intelligence reports, private letters and diaries as well as manuscripts related to secret societies. The bulk of these historical manuscripts will remain undeciphered unless we can automate the processes involved in decoding them. Our aim is to develop resources and computer-aided tools for decoding of historical source material by using AI and cross-disciplinary research involving computational linguistics, computer vision, cryptology, history, linguistics and philology.
Within the DECRYPT project, we release resources and tools with open access to facilitate research in historical cryptology, allowing collection, analysis and decipherment of historical ciphertexts. Resources are collections of encrypted sources, and historical texts with language models. The tools facilitate the processing of the encrypted sources from transcription to decipherment. We list our resources and tools below, which are described in our scientific publications.
Please, see our project website at https://de-crypt.org
The project is funded by the Swedish Research Council grant 2018-06074 DECRYPT - Decryption of historical manuscripts.
a desktop tool for breaking historical and modern ciphers
https://github.com/CrypToolProject/CrypTool-2
an online tool for breaking (simpler) historical ciphers
https://www.cryptool.org/en/cto/
a desktop tool for manual transcription
https://github.com/CrypToolProject/CTTS
a web-based tool for semi-automatic transcription using AI
https://github.com/decrypt-project/transcripttool
the web interface and API source code - a Linux-Apache-MariaDB-PHP application
https://github.com/decrypt-project/decode2
a collection of historial texts and language models for 17 European languages
https://www2.lingfil.uu.se/person/pettersson/histcorp/
statistical language models for some European historical languages
https://github.com/CrypToolProject/LanguageStatisticsLibPy
a tool for analyzing the predictability of (English) orthography using n-gram models to investigate factors influencing letter prediction accuracy
