0
A Massive Machine-Learning Approach For Classical Cipher Type Detection Using Feature Engineering
Ernst Leierzopf, Nils Kopal, Bernhard Esslinger et al., 2021. International Conference on Historical Cryptology.
Tests whether machine-learning classifiers using hand-built ciphertext features can tell apart 56 cipher types defined by the American Cryptogram Association, with neural networks doing best.
What it's used for here
The inductive methods survey notes that cipher-type classifiers like this one have no training class for verbose, mixed-key or generated text, which limits their use here.
Cited by on this site 3 records
3 methods surveys
SRCCryptanalysis, linguistics, inductive methods
Cite it
Leierzopf, E., Kopal, N., Esslinger, B., Lampesberger, H., & Hermann, E. (2021). A Massive Machine-Learning Approach For Classical Cipher Type Detection Using Feature Engineering. International Conference on Historical Cryptology. https://doi.org/10.3384/ecp183164
@article{leierzopf2021massive,
author = {Leierzopf, Ernst and Kopal, Nils and Esslinger, Bernhard and Lampesberger, Harald and Hermann, Eckehard},
title = {A Massive Machine-Learning Approach For Classical Cipher Type Detection Using Feature Engineering},
journal = {International Conference on Historical Cryptology},
year = {2021},
doi = {10.3384/ecp183164},
url = {https://doi.org/10.3384/ecp183164}
}TY - JOUR TI - A Massive Machine-Learning Approach For Classical Cipher Type Detection Using Feature Engineering AU - Leierzopf, Ernst AU - Kopal, Nils AU - Esslinger, Bernhard AU - Lampesberger, Harald AU - Hermann, Eckehard PY - 2021 JO - International Conference on Historical Cryptology DO - 10.3384/ecp183164 UR - https://doi.org/10.3384/ecp183164 ER -
Leierzopf, Ernst et al.. “A Massive Machine-Learning Approach For Classical Cipher Type Detection Using Feature Engineering.” International Conference on Historical Cryptology (2021). https://doi.org/10.3384/ecp183164.