What question did this study set out to answer?

The aim is to assess how image compression affects the performance of iris presentation attack detection systems.

June 17, 2026Signal Processing Image Communication1 citationsOpen Access

Towards compression-aware iris presentation attack detection

RARocco AlbanoRoma Tre University FBFilippo BattagliaUniversity of Messina AGAlessandro GnuttiUniversity of Brescia

Key Points

The aim is to assess how image compression affects the performance of iris presentation attack detection systems.
Evaluated transformer-based frameworks for PAD in iris recognition under various image compression techniques.
Fine-tuned models on compressed images, specifically JPEG and JPEG AI, to assess performance improvement.
Tested generalizability on learning-based codecs not used in training.
Achieved a reduction in half total error rate by 5% to 10% for images compressed at worst JPEG and JPEG AI quality settings.
Demonstrated that significant compression of embeddings does not impair PAD performance.
Found similar PAD-relevant artifacts introduced by different compression methods, ensuring model robustness.

Abstract

With the growing integration of biometric recognition systems into high-security and large-scale deployment scenarios, it is becoming increasingly important to ensure their robustness under realistic operational constraints. This implies designing solutions able to withstand potential adversarial threats that could affect their integrity and accountability, and also taking into account requirements of real-world operating systems such as limited availability of bandwidth and memory for data transmission and storage. Hence, the proposed study deals with presentation attack detection (PAD) for iris recognition, evaluating the effectiveness of Transformer-based frameworks at detecting spoofing attacks relying on fabricated or artificial biometric evidences. More specifically, we focus on the effects of image compression on the quality of iris images and on the resulting PAD performance, considering both traditional techniques such as JPEG as well as next-generation learning-based image codecs such as JPEG AI. We then examine the feasibility of mitigating compression-induced performance degradation by fine-tuning the adopted models on compressed images, achieving improvements in terms of half total error rate between 5% and 10% for images compressed at the worst JPEG and JPEG AI qualities. We also evaluate the generalizability of the developed solutions by testing them on learning-based codecs not considered during training, to check whether similar PAD-relevant artifacts are introduced by different compressions. Furthermore, we investigate the redundancy within the embeddings generated by the employed detectors, and demonstrated it is possible to significantly compress them while preserving the achievable PAD performance. Overall, the study provides a systematic analysis of iris PAD under compression constraints, offering insights into model adaptation, cross-codec robustness, and representation efficiency in scenarios where visual data coding plays a central role.

Ask AI

Helpful

Bookmark

View Full Paper