7 papers
Generalist Multimodal LLMs Gain Biometric Expertise via Human Salience
Jacob Piland, Byron Dowling, Christopher Sweet +1
Iris presentation attack detection (PAD) is critical for secure biometric deployments, yet developing specialized models faces significant practical barriers: collecting data repre…
VISER: Visually-Informed System for Enhanced Robustness in Iris Presentation Attack Detection
Byron Dowling, Jacob Piland, Eleanor Frederick +2
Human perceptual priors have shown promise in saliency-guided deep learning training, particularly in the domain of iris presentation attack detection (PAD). Common saliency approa…
When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge
Mahsa Mitcheff, Adam Czajka
Iris recognition is a mature biometric technology offering remarkable precision and speed, and allowing for large-scale deployments to populations exceeding a billion enrolled user…
Gradient-Guided Exploration of Generative Model's Latent Space for Controlled Iris Image Augmentations
Mahsa Mitcheff, Siamul Karim Khan, Adam Czajka
Developing reliable iris recognition and presentation attack detection methods requires diverse datasets that capture realistic variations in iris features and a wide spectrum of a…
Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy
Timothy Redgrave, Adam Czajka
In this work we introduce Salient Information Preserving Adversarial Training (SIP-AT), an intuitive method for relieving the robustness-accuracy trade-off incurred by traditional…
Training Better Deep Learning Models Using Human Saliency
Aidan Boyd, Patrick Tinsley, Kevin W. Bowyer +1
This work explores how human judgement about salient regions of an image can be introduced into deep convolutional neural network (DCNN) training. Traditionally, training of DCNNs…
Privacy-Safe Iris Presentation Attack Detection
Mahsa Mitcheff, Patrick Tinsley, Adam Czajka
This paper proposes a framework for a privacy-safe iris presentation attack detection (PAD) method, designed solely with synthetically-generated, identity-leakage-free iris images.…