I'm a PhD student affiliated to the Department of Electrical and Computer Engineering, Rutgers University, NJ. My research interests
are Computer Vision, Machine Learning and Biometrics. At present, my adviser at Rutgers is Prof.Vishal Patel. I'm focusing on developing deep learning based machine learning algorithms for
Active Authentication and for Biometrics applications in general. I recieved my bachelors degree in Electrical and Computer Engineering from University of Peradeniya, Sri Lanka in 2014.
Office : Room 533 CORE building
Address : ECE, 94, Brett Road, Piscataway, NJ 08854, USA.
Learning Deep Features for One-Class Classification
We propose a deep learning-based solution for the problem of feature learning in one-class classification.
The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive
features while maintaining a low intra-class variance in the feature space for the given class.
We achieve significant improvements over
the state-of-the-art in anomaly detection, novelty
detection and mobile active authentication tasks.
Efficient and Low Latency Detection of Intruders in
Mobile Active Authentication
We address the problem of quickly
detecting intrusions with lower false detection rates in mobile AA
systems with higher resource efficiency. Bayesian and Minimax
versions of the Quickest Change Detection (QCD) algorithms are
introduced to quickly detect intrusions in mobile AA systems.
These algorithms are extended with an update rule to facilitate
low frequency sensing which leads to low utilization of resources.
Journal Version ( Accepted for TIFS ).
Conference Version (BTAS '16 ). In Media (CBS news).
Towards Multiple User Active Authentication in Mobile Devices
With the advent of mobile devices a mobile device may be accessed by more than a single
enrolled user. In this context, verification of multiple enrolled users has a practical importance. We address the issue of performance degradation
associated with multiple user authentication as compared to single user authentication. We introduce the notion of probability of negativity to alleviate the effect of multiple users
in authentication. We further introduce a simple fusion scheme with the existing authentication methods to increase
the intruder detection accuracy.
Conference Version (FG '17 )
Extreme Value Analysis for Mobile Active User Authentication
In this work, we propose to improve the performance of mobile Active Authentication (AA) systems in the low false alarm region using the
statistical Extreme Value Theory (EVT). The problem is studied under a Bayesian framework where extremal observations that contribute
to mis-verification are given more prominence. We propose modeling the tail of the match distribution using a Generalized Pareto Distribution (GPD)
in order to make better inferences about the extremal observations. A method based on the mean excess function is introduced for parameter
estimation of the GPD.
Conference Version (FG '17 )
12/10/2017 : Our work on resource efficient AA has been accepted for publication at TIFS.
07/08/2017 : Our work on Active Authentication appears on CBS news!
01/23/2017 : Two papers of mine have been accepted for FG 2017!
09/08/2016 : Presented my paper on Quickest Intrusion Detection at BTAS 2016.
05/06/2016 : Presenting my work on Active Authentication at MACV 2016 at John Hopkins.
15/04/2016 : Msy work on Quickest Intrusion Detection on AA has been accepted for an oral in BTAS '16.