Authorship verification using deep belief network systems. (18th January 2017)

• Record Type: Journal Article
• Authors: Brocardo, Marcelo Luiz; Traore, Issa; Woungang, Isaac; Obaidat, Mohammad S.
• Is Part Of: International journal of communication systems. Volume 30:Number 12(2017)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2017-01-18
• Subjects: authorship verification -- continuous authentication -- Gaussian‐Bernoulli deep belief network -- stylometry; Telecommunication systems -- Periodicals; 621.382
• DOI: 10.1002/dac.3259
• Languages: English
• ISSNs: 1074-5351

Abstract

Summary: This paper explores the use of deep belief networks for authorship verification model applicable for continuous authentication (CA). The proposed approach uses Gaussian units in the visible layer to model real‐valued data on the basis of a Gaussian‐Bernoulli deep belief network. The lexical, syntactic, and application‐specific features are explored, leading to the proposal of a method to merge a pair of features into a single one. The CA is simulated by decomposing an online document into a sequence of short texts over which the CA decisions happen. The experimental evaluation of the proposed method uses block sizes of 140, 280, 500 characters, on the basis of the Twitter and Enron e‐mail corpuses. Promising results are obtained, which consist of an equal error rate varying from 8.21% to 16.73%. Using relatively smaller forgery samples, an equal error rate varying from 5.48% to 12.3% is also obtained for different block sizes. Abstract : In this paper, a novel framework for carrying continuous authentication using stylometric analysis is proposed and compared against support vector machine as a classifier. The impact of the n ‐gram model, feature merging process, and feature selection method is also studied (see above Figure 2).