DOOMGAN:High-Fidelity Dynamic Identity Obfuscation Ocular Generative Morphing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Krishnamurthy, Bharath, Rattani, Ajita
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915405843398656
author Krishnamurthy, Bharath
Rattani, Ajita
author_facet Krishnamurthy, Bharath
Rattani, Ajita
contents Ocular biometrics in the visible spectrum have emerged as a prominent modality due to their high accuracy, resistance to spoofing, and non-invasive nature. However, morphing attacks, synthetic biometric traits created by blending features from multiple individuals, threaten biometric system integrity. While extensively studied for near-infrared iris and face biometrics, morphing in visible-spectrum ocular data remains underexplored. Simulating such attacks demands advanced generation models that handle uncontrolled conditions while preserving detailed ocular features like iris boundaries and periocular textures. To address this gap, we introduce DOOMGAN, that encompasses landmark-driven encoding of visible ocular anatomy, attention-guided generation for realistic morph synthesis, and dynamic weighting of multi-faceted losses for optimized convergence. DOOMGAN achieves over 20% higher attack success rates than baseline methods under stringent thresholds, along with 20% better elliptical iris structure generation and 30% improved gaze consistency. We also release the first comprehensive ocular morphing dataset to support further research in this domain.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17158
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DOOMGAN:High-Fidelity Dynamic Identity Obfuscation Ocular Generative Morphing
Krishnamurthy, Bharath
Rattani, Ajita
Computer Vision and Pattern Recognition
Ocular biometrics in the visible spectrum have emerged as a prominent modality due to their high accuracy, resistance to spoofing, and non-invasive nature. However, morphing attacks, synthetic biometric traits created by blending features from multiple individuals, threaten biometric system integrity. While extensively studied for near-infrared iris and face biometrics, morphing in visible-spectrum ocular data remains underexplored. Simulating such attacks demands advanced generation models that handle uncontrolled conditions while preserving detailed ocular features like iris boundaries and periocular textures. To address this gap, we introduce DOOMGAN, that encompasses landmark-driven encoding of visible ocular anatomy, attention-guided generation for realistic morph synthesis, and dynamic weighting of multi-faceted losses for optimized convergence. DOOMGAN achieves over 20% higher attack success rates than baseline methods under stringent thresholds, along with 20% better elliptical iris structure generation and 30% improved gaze consistency. We also release the first comprehensive ocular morphing dataset to support further research in this domain.
title DOOMGAN:High-Fidelity Dynamic Identity Obfuscation Ocular Generative Morphing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.17158