Lecturers‎ > ‎

Karthik Nandakumar

Karthik Nandakumar

Institute for Infocomm Research
A*STAR, Singapore

Short Biography:

Karthik Nandakumar is a Scientist at Institute for Infocomm Research, A*STAR, Singapore. He received his B.E. degree (2002) from Anna University, Chennai, India, M.S. degrees in Computer Science (2005) and Statistics (2007), and Ph.D. degree in Computer Science (2008) from Michigan State University, and M.Sc. degree in Management of Technology (2012) from National University of Singapore. His research interests include statistical pattern recognition, biometric authentication, image processing, and computer vision. He has co-authored two books titled Introduction to Biometrics (Springer, 2011) and Handbook of Multibiometrics (Springer, 2006). He has received a number of awards including the 2008 Fitch H. Beach Outstanding Graduate Research Award from the College of Engineering at Michigan State University, the Best Paper award from the Pattern Recognition journal (2005), the Best Scientific Paper Award (Biometrics Track) at ICPR 2008, and the 2010 IEEE Signal Processing Society Young Author Best Paper Award.

Talk I:

Biometric Template Security: The Path Traveled and Road Ahead


With the large-scale deployment of biometric systems in various commercial and government applications, system security and user privacy issues related to biometric systems are becoming ever more important. While biometric authentication systems do not guarantee foolproof security, significant efforts have been made by the biometrics community to identify vulnerabilities and develop countermeasures to address them. Specifically, the problem of leakage of biometric information stored in the system database has been studied in depth and promising solutions have been proposed to mitigate the security and privacy concerns. This talk will discuss the recent advances that have been made in successfully reconstructing biometric data from stored templates and give an overview of various techniques that have been proposed for securing biometric templates. This presentation will show that biometric template protection algorithms can find practical acceptance only if some of the fundamental issues such as secure alignment, obtaining compact and invariant feature representations, and security analysis are addressed in a systematic manner.


Talk II:          

A Hands-On Experience with Biometric Template Protection


A number of algorithms have been proposed to enhance the security of biometric templates. In this tutorial, participants will get a hands-on experience by implementing two of the most popular template protection schemes, namely, fuzzy vault and fuzzy commitment on public-domain fingerprint and iris databases. Biometric features extracted using open-source software will be provided and the participants will be guided through the implementation of template protection process using MATLAB software. This tutorial will help the participants to appreciate the complexities and trade-offs involved in biometric template protection.