Decipherment of substitution ciphers with neural language models

Author: 
Date created: 
2018-07-26
Identifier: 
etd19821
Keywords: 
Natural Language Processing
Decipherment
Neural decipherment
Neural language models
Beam search
Abstract: 

The decipherment of homophonic substitution ciphers using language models (LMs) is a well-studied task in Natural Language Processing (NLP). Previous work in this topic score short local spans of possible plaintext decipherments using n-gram LMs. The most widely used technique is the use of beam search with n-gram LMs proposed by Nuhn et al. (2013). We propose a new approach on decipherment using a beam search algorithm that scores the entire candidate plaintext at each step with a neural LM. We augment beam search with a novel rest cost estimation that exploits the predictive power of a neural LM. This work, to our knowledge, is the first to use a large pre-trained neural language model for decipherment. Our neural decipherment approach outperforms the state-of-the-art n-gram based methods on many different ciphers. On challenging ciphers such as the Beale cipher our system reports significantly lower error rates with much smaller beam sizes.

Document type: 
Thesis
Rights: 
This thesis may be printed or downloaded for non-commercial research and scholarly purposes. Copyright remains with the author.
File(s): 
Supervisor(s): 
Anoop Sarkar
Department: 
Applied Sciences: School of Computing Science
Thesis type: 
(Thesis) M.Sc.
Statistics: