Automated detection of unstructured context-dependent sensitive information using deep learning

DOI	Resolve DOI: https://doi.org/10.1016/j.iot.2021.100444
Author	Search for: Ahmed, Hadeer ORCID identifier: https://orcid.org/0000-0001-9568-1563; Search for: Traore, Issa; Search for: Saad, Sherif; Search for: Mamun, Mohammad¹
Affiliation	National Research Council Canada. Digital Technologies
Format	Text, Article
Subject	machine learning; deep learning; NLP; data leak prevention; unstructured data; sensitive data
Abstract	With the rapid growth of cloud computing and remote workforces, organizations are increasingly aware of the risk of data leaks and data exfiltration. Handling such risk has become more challenging because organizations today usually deal with big data. In particular, organizations must deal with massive amounts of unstructured data. As a result, modern data leak prevention (DLP) solutions must support automated methods to detect and identify confidential and sensitive information in both structured and unstructured data. In this paper, we demonstrate the benefits of using deep learning to identify unstructured context-dependent sensitive information, in contrast to traditional machine learning methods and rule-based methods.
Publication date	2021-08-14
Publisher	Elsevier
In	Internet of Things 16, 100444 (December 2021).
Language	English
Peer reviewed	Yes
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	80a99e7b-7412-4657-a1fa-f6d3ef70df3f
Record created	2021-09-10
Record modified	2021-09-14

Page details