Deep Learning Application – Identifying PII (Personally Identifiable Information) to Protect

Anil K. Makhija
Additional contact information
Anil K. Makhija: CamEd Business School, Cambodia

Journal of Accounting, Finance, Economics, and Social Sciences, 2020, vol. 5, issue 2, 10-16

Abstract: This paper presents application of deep learning and machine learning models in detecting personally identifiable information (PII) in unstructured text (emails). The proposed models use support vector machine (trained using sequential minimal optimization) and long short term memory (LSTM) artificial neural network. Synthetic email dataset has been used to train and validate the proposed models and the outcomes are measured by standard measures of accuracy, precision, recall and F1-score of each of the proposed model. The experimental results on the model that uses support vector machine (trained using sequential minimal optimization) showed most promising results on detecting the personally identifiable information in the email dataset. The LSTM model also showed equally promising results.

Keywords: Personally Identifiable Information; Deep Learning in detecting PII; Machine Learning in detecting PII; Artificial Intelligence in protecting privacy; Protecting Personally Identifiable Information (search for similar items in EconPapers)
Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
https://jafess.com/index.php/home/article/view/23 Abstract page (text/html)
https://jafess.com/index.php/home/article/download/23/19 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:euj:jafess:v:5:y:2020:i:2:id:23

DOI: 10.62458/jafess.160224.5(2)10-16

Access Statistics for this article

More articles in Journal of Accounting, Finance, Economics, and Social Sciences from CamEd Business School
Bibliographic data for series maintained by Narin Choeun ().