Dr. Nalini K. Ratha
IBM Watson Research Center
19 Skyline Drive, Hawthorne, NY 10532
Phone: 914-784-7136
Fax: 914-784-7455
Email: ratha@us.ibm.com
DVP term expires December 2012
Dr. Nalini K. Ratha is a Research Staff Member at IBM Thomas J. Watson Research Center, Hawthorne NY where he is the team leader for the biometrics-based authentication research. He is an adjunct professor at Cooper Union and NYU-Poly. He has over 20 years of experience in the industry working in the area of pattern recognition, computer vision and image processing. He received his B. Tech. in Elelectrical Engineering from Indian Institute of Technology, Kanpur, M.Tech. degree in Computer Science and Engineering also from Indian Institute of Technology, Kanpur and Ph. D. in Computer Science from Michigan State University. Before joining IBM Research, he worked at CMC R&D center and ECIL Computer Group both in India. He has authored more than 70 research papers in the area of biometrics and has been co-chair of several leading biometrics conferences and serves on the editorial boards of IEEE Trans. on PAMI and IEEE Trans. on SMC-B. He has co-authored a popular book on biometrics entitled “Guide to Biometrics” and also co-edited two books entitled “Automatic Fingerprint Recognition Systems” and “Advances in Biometrics: Sensors, Algorithms and Systems”. He has offered tutorials on biometrics technology at leading IEEE conferences and also teaches courses on biometrics and security. He is Fellow of IEEE, Fellow of IAPR and a member for ACM. His research interests include biometrics, pattern recognition and computer vision.
Biometrics Search: Finding a Needle in a Haystack
Abstract: To search a biometrics template in a large collection is an extremely challenging task based on the fact that biometrics signals have a very high intra-class variability. Often the current approaches carry out a repeated 1:1 search over large databases which have two drawbacks in terms of not being scalable and also increasing the underlying error rates. Novel local meta-feature based biometrics search holds a lots of promise. This talk addresses some of the challenges and how efficient indexing can be achieved to exploit searching on large biometrics databases.
Can Biometrics Improve Security?
It is commonly believed that biometrics when introduced in an authentication system can improve the overall security of the system. Based on a pattern recognition model of biometrics-based authentication system, we argue that when properly designed a biometrics-based authentication system can be highly secure. We identify several attack points in a biometrics-based authentication system and propose counter measures to thwart the attacks. With the improved awareness of the possible attacks, systems incorporating biometrics can be built with higher security.
Privacy Enhancement in Biometrics
Biometrics, as an authentication tool, provides several advantages over conventional what you know (e.g., password, PIN) and what you possess (e.g., keys, tokens) authentication methods. However, a biometrics is an irrevocable password as we can’t change the biometrics easily. If it is compromised digitally, it is compromised for ever. Secondly, a biometrics can be easily matched against multiple databases to link identities. In order to alleviate privacy deficiencies of biometrics, new techniques for protecting biometrics templates that can allow for revocation and anonymous sharing need to be developed. Instead of enrolling with the true biometrics, the original signal/template is intentionally and repeatably distorted using a class of non-invertible functions. The resulting “transformed” biometrics is enrolled. During verification, the same distortion transformation is applied to the biometrics signal/template to match against the enrolled template. The proposed method supports revocability and permits anonymous matching where biometrics data sharing is prohibited.
