LivDet-Iris 2025 is the sixth edition of the iris liveness detection competition. Held every two to three years, the competition aims to foster the development of robust algorithms capable of detecting a wide range of physically-and digitally-presented attacks in iris biometrics. The 2025 edition obtained the largest number of submissions in the history of the competition: ten algorithms from five institutions, and one commercial iris recognition system. LivDet-Iris 2025 also introduced new tasks compared to previous editions: (Task 1) a benchmark offered by an industry partner, (Task 2) morphed iris images, in which two different-identity samples were blended into one image, and (Task 3) evaluation of presentation attack detection robustness against advanced manufacturing techniques for textured contact lenses. This edition, for the first time in the series, offers a systematic testing of a commercial iris recognition system (software and hardware) using physical artifacts presented to the sensor. Dermalog-Iris team submitted algorithms that won all tasks, achieving the area under the ROC curve of 90.57%, 68.23% and 99.99% in tasks 1, 2, and 3, respectively. Additionally, we include results for baseline algorithms, based on modern deep convolutional neural networks and trained with all available public datasets of iris images representing bona fide samples and anomalies (physical attacks, eye diseases, post-mortem cases, and synthetically-generated iris images). Test samples created for tasks 2 and 3, and baseline models are made available to offer the state-of-the-art benchmark for iris liveness detection.

The demand for presentation attack detection (PAD) to identify fraudulent identity documents in remote verification systems has experienced considerable expansion in recent years. This increase is the result of several factors, such as the rise of remote working, online shopping, migration and advances in synthetic imaging. Additionally, an increase in the number of attacks targeting the enrollment process has been noted. Training a PAD system to detect fraudulent identity documents is challenging due to the limited number of available identity documents, as collecting identity passports raises privacy concerns. To address the scarcity of available data, this work proposes a new, realistic ICAO-compliant passport dataset generated using a novel hybrid method that combines synthetic data with open-access information. Experimental evaluation in challenging environments validates the utility of synthetic data. A commercial off-the-shelf PAD algorithm trained on real data computes a detection equal error rate of 19% when using the proposed synthetic dataset for testing1.