Latifah Abduh
Colour Processing in Adversarial Attacks on Face Liveness Systems
Abduh, Latifah; Ivrissimtzis, Ioannis; Vidal, Franck P.; Tam, Gary K.L.; Roberts, Jonathan C.
Authors
Dr Ioannis Ivrissimtzis ioannis.ivrissimtzis@durham.ac.uk
Associate Professor
Franck P. Vidal
Gary K.L. Tam
Jonathan C. Roberts
Abstract
In the context of face recognition systems, liveness test is a binary classification task aiming at distinguishing between input images that come from real people’s faces and input images that come from photos or videos of those faces, and presented to the system’s camera by an attacker. In this paper, we train the state-of-the-art, general purpose deep neural network ResNet for liveness testing, and measure the effect on its performance of adversarial attacks based on the manipulation of the saturation component of the imposter images. Our findings suggest that higher saturation values in the imposter images lead to a decrease in the network’s performance. Next, we study the relationship between the proposed adversarial attacks and corresponding direct presentation attacks. Initial results on a small dataset of processed images which are then printed on paper or displayed on an LCD or a mobile phone screen, show that higher saturation values lead to higher values in the network’s loss function, indicating that these colour manipulation techniques can indeed be converted into enhanced presentation attacks.
Citation
Abduh, L., Ivrissimtzis, I., Vidal, F. P., Tam, G. K., & Roberts, J. C. (2019). Colour Processing in Adversarial Attacks on Face Liveness Systems. In Proceedings of Computer Graphics and Visual Computing 2019 (CGVC) (149-152). https://doi.org/10.2312/cgvc.20191272
Conference Name | Computer Graphics and Visual Computing (CGVC) |
---|---|
Conference Location | Bangor, UK |
Acceptance Date | Jul 22, 2019 |
Publication Date | 2019 |
Deposit Date | Sep 13, 2019 |
Publicly Available Date | Dec 3, 2020 |
Pages | 149-152 |
Book Title | Proceedings of Computer Graphics and Visual Computing 2019 (CGVC). |
DOI | https://doi.org/10.2312/cgvc.20191272 |
Files
Accepted Conference Proceeding
(1.3 Mb)
PDF
Copyright Statement
This is the accepted version of the following article: Abduh, Latifah & Ivrissimtzis, Ioannis (2019), Colour Processing in Adversarial Attacks on Face Liveness Systems, in Vidal, Franck P., Tam, Gary K. L. & Roberts, Jonathan C. eds, Computer Graphics and Visual Computing (CGVC). Bangor, UK, The Eurographics Association, 149-152 which has been published in final form at http://doi.org/10.2312/cgvc.20191272
You might also like
Anomaly Detection with Transformers in Face Anti-spoofing
(2023)
Conference Proceeding
Exploring the Potential of Immersive Virtual Environments for Learning American Sign Language
(2023)
Conference Proceeding
Developing and Evaluating a Novel Gamified Virtual Learning Environment for ASL
(2023)
Conference Proceeding
Race Bias Analysis of Bona Fide Errors in Face Anti-spoofing
(2023)
Conference Proceeding
Bivariate non-uniform subdivision schemes based on L-systems
(2023)
Journal Article