Keynote Speakers

Rasa Karbauskaite (FRONTEX) - Implementation and operational Impact of Biometric Systems for Border Control

Abstract

European border management is currently undergoing significant transformation and facing new and evolving challenges. Biometric technology plays a significant role in enabling and facilitating more modern, effective and efficient border management in the Schengen area. The existing and future information systems in the EU for border management and internal security relies on biometric data an interoperability.

The use of biometric systems for border control constitutes operational and technical challenges. It changes the border checks process, has a significant impact on day-to-day operations and creates new risks and vulnerabilities.

Frontex supports Member States in harmonised implementation and operationalisation of new systems at external borders by developing capability tools such as best practices, guidelines, risk management framework and training, just to name a few

 

CV

Rasa Karbauskaite joined Frontex Research and Development Unit in 2006. She works as a Senior Research Officer and is leading the Harmonisation of the EU Border Control Capacities project which among other objectives focuses on development of standards and capability tools for border control. Previously she managed the Future of Border Checks and Automated Border Control solutions projects at Frontex. In the past, she  lead the BIOPASS I and II studies primarily focused on application of biometric technology for border control, in particular, implementation of ABC solutions  in Europe and outside it.

Since 2010, she was also leading the ABC Working Group tasked to elaborate best practice guidelines for ABC and to serve as a forum for sharing operational and technical experience pertaining to ABC. The results include development of Best Practice Operational and Technical Guidelines for ABC and of harmonised trainings on ABC system including on vulnerability assessment and testing.

Rasa is participating in a number of international working groups and standardization fora including ISO, CEN and ICAO work. As of 2017, she also serves for the management board of the European Association of Biometrics (EAB).

Prior to joining Frontex in 2006, Rasa has worked at DePaul University (United States) on research projects related to US-Mexico migration and immigrants in the labour force. She holds a MA in International Studies (United Sates) and a BA in Social Geography (Lithuania). She has received training in Military Operational Research as well as Strategic Development and Planning in Security Sector from Cranfield Defence Academy (United Kingdom). Rasa also holds a Diploma in Demography and Geodemography from Charles University (Czech Republic).  

 

 

Patrick Grother (NIST) - Results of the Face Recognition Vendor Test 2018

Abstract

FRVT 2018 is being conducted to assess state-of-the-art face recognition accuracy.  In April 2014, NIST Interagency Report 8009 documented accuracy of algorithms supplied to NIST in October 2013 applied to identification of cooperative mugshot-style images.  The best result, for an NEC algorithm, was a rank 1 miss rate of 4.1% (FNIR = 0.041, N = 1,600,000, T = 0, single image enrollment), with the next best developer at 9.1%.  Re-running the identical experiment with February 2018 algorithms has yielded a miss rate below 0.4%, with algorithms from 16 of 32 developers beating the 2013 NEC benchmark.

This remarkable improvement, obtained on images with imperfect ISO/IEC 19794-5 conformance, shows that the new generation of CNN-based algorithms have been adopted by developers and should replace the operationally installed base.   The question, advanced as CNN results first appeared in the literature, of whether they would demonstrate discrimination ability – key for large N – in addition to their famous invariance properties (pose, illumination etc.) is also addressed.  FRVT 2018 includes results for N up to 12 million and for high-threshold, low false positive identification rates (FPIR below 0.001). These show large, but reduced, gains since 2013.  The study includes results also for wild, webcam and surveillance images.

Implementations vary: a wide range of performance remains across the industry, with accuracy spanning more than an order of magnitude.  Speed varies greatly also, with template generation and search times varying by one and two orders of magnitude respectively.  A few algorithms demonstrate search durations that grow very sub-linearly with N, but at the expense of initially building fast-search data structures.  The FRVT 2018 will document effects of image-specific and subject-specific covariates on accuracy, including age, ageing, sex and race.  The results will be previewed and contributed to the ISO/IEC 22116 project on differential impacts of demographics in biometrics.

CV

Patrick Grother is a computer scientist at the U.S. National Institute of Standards and Technology (NIST). First employed there in 1990, he has supervised a team of six biometrics researchers since 2007 assisting a number of US Government agencies on research, development and evaluation of biometric.

Since 2000, his work has been exclusively in biometrics, particularly on the evaluation of face, iris and fingerprint recognition algorithms. He leads the IREX, FRVT and FIVE evaluations of iris and face recognition technologies that support biometrics in national scale identity management, and which provide quantitative support to standards developed in SC 37.

His research interests include performance metrics, image quality, the zoo, scalability, permanence, vulnerabilities and fusion. His standards activities are in testing and reporting, data formats, image quality. He serves as acting chairman of SC37

 

 

Stephanie Schuckers (Clarkson University) - The Coming of Age of Presentation Attack Detection

Abstract

“Presentation attacks” are attacks at a biometric recognition data capture sensor which interfere with its normal operation.  Such attacks could include artefacts with biometric characteristics such as printouts, image/video display, or reproductions made of gelatin, glue, silicon, or plastic. Software and hardware-based “presentation attack detection (PAD)” components have been developed to reduce this vulnerability.  Over the last twenty years of research and development, it has been more commonly termed spoofing and the methods used to detect spoofs have been called liveness detection.  

Biometric recognition systems which include PAD are coming of age with wide-spread commercialization. This is motivated by the recognition of the need to minimize this vulnerability as biometric technology explodes particularly in the consumer marketplace. 

This talk gives an overview of this field, describes vocabulary formalized by the ISO standard for biometric presentation attack detection, and discusses evaluating the performance of systems which incorporate methods to detect and reject presentation attacks.  Some considerations for the future of presentation attack detection are discussed.

 

CV

Dr. Stephanie Schuckers is the Paynter-Krigman Endowed Professor in Engineering Science in the Department of Electrical and Computer Engineering at Clarkson University and serves as the Director of the Center of Identification Technology Research (CITeR), a National Science Foundation Industry/University Cooperative Research Center. 

She received her doctoral degree in Electrical Engineering from The University of Michigan. Professor Schuckers research focuses on processing and interpreting signals which arise from the human body. 

Her work is funded from various sources, including National Science Foundations Department of Homeland Security, and private industry, among others.  She has started her own business, testified for US Congress, and has over 40 journal publications as well as over 60 other academic publications.