Outputs (3)

Colour Processing in Adversarial Attacks on Face Liveness Systems (2019)
Presentation / Conference Contribution
Abduh, L., & Ivrissimtzis, I. (2019, December). Colour Processing in Adversarial Attacks on Face Liveness Systems. Presented at Computer Graphics and Visual Computing (CGVC), Bangor, UK

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... Read More about Colour Processing in Adversarial Attacks on Face Liveness Systems.

Using theoretical ROC curves for analysing machine learning binary classifiers (2019)
Journal Article
Omar, L., & Ivrissimtzis, I. (2019). Using theoretical ROC curves for analysing machine learning binary classifiers. Pattern Recognition Letters, 128, 447-451. https://doi.org/10.1016/j.patrec.2019.10.004

Most binary classifiers work by processing the input to produce a scalar response and comparing it to a threshold value. The various measures of classifier performance assume, explicitly or implicitly, probability distributions Ps and Pn of the respo... Read More about Using theoretical ROC curves for analysing machine learning binary classifiers.

Trivalent expanders, $(Delta – Y)$-transformation, and hyperbolic surfaces (2019)
Journal Article
Ivrissimtzis, I., Peyerimhoff, N., & Vdovina, A. (2019). Trivalent expanders, $(Delta – Y)$-transformation, and hyperbolic surfaces. Groups, Geometry, and Dynamics, 13(3), 1103-1131. https://doi.org/10.4171/ggd/518

We construct a new family of trivalent expanders tessellating hyperbolic surfaces with large isometry groups. These graphs are obtained from a family of Cayley graphs of nilpotent groups via (Delta–Y)-transformations. We study combinatorial, topologi... Read More about Trivalent expanders, $(Delta – Y)$-transformation, and hyperbolic surfaces.