Novel User Level Data Leakage Detection Algorithm
T.Lakshmi Siva Rama Krishna1, P.Bandavi2, K.Priyanka3, V.P.Vivek4

1T.Lakshmi Siva Rama Krishna*, Assistant Professor, QIS College of Engineering & Technology (Autonomous), Ongole, AP, India
2P.Bandavi, Assistant Professor, QIS College of Engineering & Technology (Autonomous), Ongole, AP, India
3K.Priyanka, Assistant Professor, QIS College of Engineering & Technology (Autonomous), Ongole, AP, India
4V.P.Vivek, Assistant Professor, QIS College of Engineering & Technology (Autonomous), Ongole, AP, India

Manuscript received on 02 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 August 2019 | PP: 2378-2381| Volume-8 Issue-10, August 2019 | Retrieval Number: G5313058719/2019©BEIESP | DOI: 10.35940/ijitee.G5313.0881019
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Data leakage detection (DLD) is the most widely used detection technique in many applications such as etc. detecting data leakage by various data sources is an important research issue. Several researchers contributed to detect the data leakage by proposing various techniques. In the existing DLD techniques the performance metrics such as accuracy and time have been neglected. In this paper, we have proposed a new DLD algorithm and named it as novel user level data leakage detection algorithm (NULDLDA). In the proposed NULDLDA we have considered the user point of view to know the leakage of data by which agent among several existing agents. We have implemented and compared the NULDLDA with existing DLD. The experimental results indicate that proposed NULDLDA improved the performance over DLD with respect to time and accuracy.
Keywords: IT; watermarking guilty agent; explicit data; DLP (data leakage prevention)
Scope of the Article: Data Analytics