Monday, September 25th, 2023
09.00 – 14-30
Union Hall (Grand Hotel Union)
In conjunction with the IEEE International Joint Conference on Biometrics (IJCB 2023)
Presenters:
-
- Guido Borghi, PhD – University of Bologna
- Nicolò Di Domenico – University of Bologna
- Lorenzo Pellegrini, PhD – University of Bologna

Abstract
Face recognition technology has gained widespread prominence due to its multifaceted applications across various domains, ranging from identity verification to personalized user experiences, and therefore the need for secure and efficient facial identity verification has become crucial. Ensuring the robustness of Face Recognition and Verification systems against malicious attempts to bypass or impersonate users is vital to safeguard individuals and organizations from potential cyber threats. In particular, the Morphing Attack, i.e., the possibility of eluding face verification systems through a facial morphing operation between a criminal and an accomplice, has recently emerged as a serious security threat. Despite the importance of this kind of attack, the development and comparison of Morphing Attack Detection (MAD) methods is still a challenging task, especially with solutions based on deep learning approaches. Therefore, we have developed and publicly released Revelio, a flexible and modular framework for the reproducible development and evaluation of MAD systems. After an analysis of the recent trend of Face Recognition systems available in the market and in the literature, we will show how it is possible to use the Revelio framework to develop and deploy effective Single Image MAD (S-MAD) and Differential MAD (D-MAD) algorithms on publicly released datasets, even obtaining state-of-the-art performance. Finally, we will show and illustrate the use of the FVC-onGoing and NIST MORPH FRVT, web platforms that can be used to effectively test MAD systems on sequestered datasets.
Pre-requisites for the partecipants
Basic programming skills in Python, PyTorch, and concepts of Machine and Deep Learning.
All concepts will be introduced and explained to encourage active participation from the entire audience.
Program
- Introduction to Face Recognition and Verification
-
- Recent trends in the literature
- Analysis of commercial systems
- Analysis of the potential security threats
-
- Introduction to the Face Morphing security threat and MAD systems
- Introduction to the Revelio framework
- Datasets availability, loading and data pre-processing
- Face detection module
- Forensic feature extraction module
- Model design and training
- Evaluation procedures
- Developing a S-MAD method using Revelio
- Developing a D-MAD method using Revelio
Material
TBD
References
- Matteo F., Franco A. and Maltoni D. The magic passport (IJCB 2014)
- Raja K. et al. Morphing attack detection-database, evaluation platform, and benchmarking (TIFS 2020)
- https://miatbiolab.csr.unibo.it/revelio-framework/
- Borghi G. et al. A double siamese framework for differential morphing attack detection (Sensors 2021)
- Dorizzi B. et al. Fingerprint and on-line signature verification competitions at ICB 2009 (ICB 2009)
- https://biolab.csr.unibo.it/fvcongoing