• home
• current students
• graduate
• events

Presenter: Hanan Alhindi
Supervisor:

Date: Thu, August 23, 2018
Time: 11:00:00 - 00:00:00
Place: EOW 430

ABSTRACT

ABSTRACT:

One of the main threats faced by any organization that maintains sensitive digital assets is the threat posed by malicious insiders. Some of these insiders, whose aim is to threaten the organization’s security, leverage their privileges to leak sensitive data. Because of that, organizations aim to enhance their internal security by deploying data protection, and insider threat detection and prevention schemes. Data loss prevention

(DLP) is an emerging mechanism that is currently being used by organizations to detect and block unauthorized data transfers. Existing DLP approaches, however, face several practical challenges that limit their effectiveness. In our research, we present a new DLP approach that addresses many existing challenges by extracting and analyzing document content semantics. We introduce the notion of a document semantic signature as a summarized representation of the document semantic. We show that the semantic signature can be used to detect a data leak by experimenting on a public dataset, yielding very encouraging detection effectiveness results. In addition, we show a comparative evaluation of our model with several data loss prevention models.