Biometric Authentication with a Timeless Learner
Description
Biometrics systems are vulnerable to well-crafted presentation attacks. Under IARPA’s Odin/Thor program, ISI researchers are creating systems and algorithms resilient to presentation attacks (spoofing) of biometric authentication systems, including the face, iris and fingerprint systems. Partners include the Switzerland-based Idiap Research Institute, TU Darmstadt, TREX Enterprises, and Northrup Grumman.
Team
Publications
Explaining Face Presentation Attack Detection Using Natural Language
December 15, 2021
IEEE International Conference
A large number of deep neural network-based techniques have been developed to address the challenging problem of face presentation attack detection (PAD). Whereas such techniques’ focus has been on improving PAD performance in terms of classification accuracy and robustness against unseen attacks and environmental conditions, there exists little attention on the explainability of PAD predictions.
In this paper, we tackle the problem of explaining PAD predictions through natural language.
Multi-Modal Fingerprint Presentation Attack Detection: Evaluation on A New Dataset
April 9, 2021
IEEE Transactions on Biometrics, Behavior, and Identity Science
Fingerprint presentation attack detection is becoming an increasingly challenging problem due to the continuous advancement of attack preparation techniques, which generate realistic-looking fake fingerprint presentations. In this work, rather than relying on legacy fingerprint images, which are widely used in the community, we study the usefulness of multiple recently introduced sensing modalities. Our study covers front-illumination imaging using short-wave-infrared, near-infrared, and laser illumination; and back-illumination imaging using near-infrared light.
Multispectral Biometrics System Framework: Application to Presentation Attack Detection
April 9, 2021
IEEE Sensors Journal (JSEN)
In this work, we present a general framework for building a biometrics system capable of capturing multispectral data from a series of sensors synchronized with active illumination sources. The framework unifies the system design for different biometric modalities and its realization on face, finger and iris data is described in detail.
Detection and Continual Learning of Novel Face Presentation Attacks
April 9, 2021
International Conference on Computer Vision
In this work, we present a general framework for building a biometrics system capable of capturing multispectral data from a series of sensors synchronized with active illumination sources. The framework unifies the system design for different biometric modalities and its realization on face, finger and iris data is described in detail.
Sponsors
Intelligence Advanced Research Projects Activity
SPONSOR PROGRAM: ODIN – THOR
CONTRACT: 2017-17020200005