Xiaoming Liu

[intermediate] Deep Learning for Trustworthy Biometrics

Summary

In recent years we have witnessed increasingly diverse application scenarios of biometrics in our daily life, despite the societal concerns on some of the weaknesses of the technology. A sustainable deployment and prospects of biometric systems will rely heavily on the ability to trust the recognition process and its output. As a result, in addition to the high recognition accuracy, trustworthy biometrics has become an emerging research area, with topics ranging from biometrics security (e.g., presentation attack detection and forgery detection), biasness in biometrics, adversarial robustness, to interpretable biometrics. In this course, we will present some of the recent works on these topics and discuss the remaining issues warranting future research.

Syllabus

• Deep learning for presentation attack detection (anti-spoofing)
• Mitigate biasness in face recognition
• Deepfake or image manipulation detection and localization
• Adversarial attack detection
• Reverse engineering of the deepfakes

References

Xiao Guo, Yaojie Liu, Anil Jain, Xiaoming Liu, “Multi-domain Learning for Updating Face Anti-spoofing Models,” in Proceeding of European Conference on Computer Vision (ECCV) 2022, Tel-Aviv, Israel, October 2022. (Oral)

Yaojie Liu, Joel Stehouwer, Xiaoming Liu, “On Disentangling Spoof Traces for Generic Face Anti-Spoofing,” in Proceeding of European Conference on Computer Vision (ECCV) 2020, Glasgow, UK, August 2020.

Yaojie Liu, Joel Stehouwer, Amin Jourabloo, Xiaoming Liu, “Deep Tree Learning for Zero-shot Face Anti-Spoofing,” in Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR) 2019, Long Beach, CA, June 2019.

Yaojie Liu, Amin Jourabloo, Xiaoming Liu, “Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision,” in Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR) 2018, Salt Lake City, UT, June 2018.

Hao Dang, Feng Liu, Joel Stehouwer, Xiaoming Liu, Anil Jain, “On the Detection of Digital Face Manipulation,” in Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR) 2020, Seattle, WA, June 2020.

Debayan Deb, Xiaoming Liu, Anil Jain, “FaceGuard: A Self-Supervised Defense Against Adversarial Face Images,” in Proceedings of the 17th International Conference on Automatic Face and Gesture Recognition (FG) 2023, Hawaii, USA, January 2023.

Vishal Asnani, Xi Yin, Tal Hassner, Sijia Liu, Xiaoming Liu, “Proactive Image Manipulation Detection,” in Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR) 2022, New Orleans, LA, June 2022.

Sixue Gong, Xiaoming Liu, Anil Jain, “Mitigating Face Recognition Bias via Group Adaptive Classifier,” in Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR) 2021, Nashville, TN, June 2021.

Sixue Gong, Xiaoming Liu, Anil Jain, “Jointly De-biasing Face Recognition and Demographic Attribute Estimation,” in Proceeding of European Conference on Computer Vision (ECCV) 2020, Glasgow, UK, August 2020.

Bangjie Yin, Luan Tran, Haoxiang Li, Xiaohui Shen, Xiaoming Liu, “Towards Interpretable Face Recognition,” in Proceeding of International Conference on Computer Vision (ICCV) 2019, Seoul, South Korea, October 2019.

Pre-requisites

Basic machine learning and computer vision knowledge.

Short bio

Dr. Xiaoming Liu is the MSU Foundation Professor and Anil and Nandita Jain Endowed Professor at the Department of Computer Science and Engineering of Michigan State University (MSU). He received Ph.D. degree from Carnegie Mellon University in 2004. Before joining MSU in 2012, he was a research scientist at General Electric (GE) Global Research. He works on computer vision, machine learning and biometrics, especially on face related analysis and 3D vision. Since 2012, he helps to develop a strong computer vision area in MSU, who is ranked top 15 in US according to the 5-year statistics at csrankings.org. He has been Area Chair for numerous conferences, the Co-Program Chair of BTAS’18, WACV’18, IJCB’22, and AVSS’22 conferences and Co-General Chair of FG’23 conference. He is an Associate Editor of Pattern Recognition and IEEE Transactions on Image Processing. His work has been cited over 20,000 times according to Google Scholar with an H-index of 68. He is a Fellow of the Institute of Electrical and Electronics Engineers (IEEE) and the International Association for Pattern Recognition (IAPR). His research has been widely reported in prominent national and international news outlets, including The Wall Street Journal, CNBC, CNET, Engadget, Fortune, The Mac Observer, etc. More information of Dr. Liu’s research can be found at http://cvlab.cse.msu.edu.