| Title | : | Semi-adversarial AutoEncoders for Imparting Privacy to Face Images |
| Speaker | : | Arun Ross (Michigan State University) |
| Details | : | Fri, 8 Mar, 2019 3:00 PM @ A M Turing Hall |
| Abstract: | : | Biometrics is the science of recognizing individuals based on their physical and behavioral attributes such as fingerprints, face, iris, voice and gait. The past decade has witnessed tremendous progress in this field, including the deployment of biometric solutions in diverse applications such as border security, national ID cards, amusement parks, access control, and smartphones. Despite these advancements, biometric systems have to contend with a number of challenges related to data quality, presentation attacks, and personal privacy. For example, a biometric system is vulnerable to spoof attacks where an adversary imitates the biometric trait (e.g., fingerprint) of another person. Further, issues related to information leakage, where the biometric data of an individual is processed to extract additional information (such as age, gender, race, etc.) beyond what was expressed at the time of data collection, can undermine personal privacy. This talk will highlight some of the recent progress made in the field of biometrics; present our labs work on presentation attack detection and privacy impartation to biometric data; and discuss some of the challenges that have to be solved in order to promote the widespread use of this technology. |
