Solving Historical Dictionary Codes with a Neural Language Model
This solves a specific historical cryptanalysis problem for researchers, but it is incremental as it applies existing neural methods to a new dataset.
The paper tackled the problem of deciphering historical dictionary codes by constructing a decoding lattice and searching it with a neural language model, achieving 75.1% correct decipherment of cipher-word tokens in letters from the late 1700s and early 1800s.
We solve difficult word-based substitution codes by constructing a decoding lattice and searching that lattice with a neural language model. We apply our method to a set of enciphered letters exchanged between US Army General James Wilkinson and agents of the Spanish Crown in the late 1700s and early 1800s, obtained from the US Library of Congress. We are able to decipher 75.1% of the cipher-word tokens correctly.