Mysteries Department
Sign inRequest access
0

Can Sequence-to-Sequence Models Crack Substitution Ciphers?

Nada Aldarrab, Jonathan May, 2021. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers).

Trains a character-level transformer to decode simple substitution ciphers directly, without searching for a key, and tests it on unseen keys and on several plaintext languages.

MYS08HTEHX052AX · mystery · click to copyMVoynich ManuscriptArticledoi: 10.18653/v1/2021.acl-long.561Checked against the original0

What it's used for here

The cryptanalysis survey lists it among neural decipherment methods, and the inductive-methods survey includes it in its references.

Cited by on this site 2 records

2 methods surveys
Cryptanalysis, inductive methods
SRC

Cite it

Aldarrab, N., & May, J. (2021). Can Sequence-to-Sequence Models Crack Substitution Ciphers?. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). https://doi.org/10.18653/v1/2021.acl-long.561
Private beta Downloads are for beta members

We're in a private beta while we get things right. Everything here is free to read; downloading datasets, sources and code is open to members for now.

It takes a couple of minutes. We'll reply by email.