A Systematic Failure Analysis of Vision Foundation Models for Open Set Iris Presentation Attack Detection

• URL: http://arxiv.org/abs/2605.19020v1
• Date: Mon, 18 May 2026 18:41:26 GMT
• Title: A Systematic Failure Analysis of Vision Foundation Models for Open Set Iris Presentation Attack Detection
• Abstract summary: This work presents a systematic failure analysis of general-purpose vision foundation models for open-set iris PAD using periocular imagery.<n>Results indicate that foundation models can transfer across datasets with similar sensing characteristics, but fail to generalise reliably to unseen attack instruments.<n>These findings show that strong closed-set or cross-dataset performance should not be treated as evidence of robust open-set security.
• Score: 6.472008340680056
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision foundation models have demonstrated strong transferability across diverse visual recognition tasks and are increasingly considered for biometric applications. Their suitability for iris Presentation Attack Detection (PAD), particularly under realistic open-set operating conditions, remains insufficiently examined. This work presents a systematic failure analysis of general-purpose vision foundation models for open-set iris PAD using periocular imagery. Five representative foundation models are evaluated under three open-set protocols that explicitly separate different sources of distribution shift: unseen Presentation Attack Instruments (PAIs), unseen datasets captured with different sensors and cross-spectral transfer from near-infrared (NIR) to visible spectrum (VIS) imagery. Both frozen feature representations and parameter-efficient task adaptation using Low-Rank Adaptation (LoRA) are assessed within a unified experimental framework. The results indicate that foundation models can transfer across datasets with similar sensing characteristics, but fail to generalise reliably to unseen attack instruments and degrade sharply under cross-spectral evaluation. While LoRA improves performance in certain cross-dataset settings, it frequently amplifies failure under attack-level and spectral shifts. Additional validation experiments using segmented iris inputs, full backbone fine-tuning, joint cross-dataset and cross-PAI shifts, and reverse VIS to NIR transfer further confirm that these failures are not simply artefacts of periocular input, weak adaptation, or one-directional spectral evaluation. These findings show that strong closed-set or cross-dataset performance should not be treated as evidence of robust open-set security, and highlight the need for PAD representations that maintain sensitivity to presentation artefacts while remaining stable under realistic deployment variation.

Related papers

• Operational Range Bounding in Spectroscopy: A Safety Cage Framework for Machine Learning Models [0.6908439820101059]
  This study evaluates a modular safety cage architecture that operates as a parallel monitoring layer to assess the validity of a prediction.<n>No single indicator captures all failure modes, demonstrating the need for indicator fusion.<n>Using a formalised coverage-risk framework, a systematic analysis of indicator combinations is performed to identify configurations that maximise risk-ranking accuracy.
  arXiv  Detail & Related papers  (2026-09-11T20:32:01Z)
• Bridging Severe Cross-Modal Misalignment: End-to-End Visible-Infrared Object Detection via Explicit Feature-Domain Affine Registration [17.74037850404483]
  We propose an end-to-end visible-infrared oriented object detector tailored for severely cross-modal geometric discrepancies.<n>The proposed JFRDet achieves 69.7% $mathrmmAP_50$ on DroneVehicle Misaligned (DVMA), which represents state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-08-11T09:02:37Z)
• AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors [11.468095590140777]
  AEGIS is a semantic aware and uncertainty guided adversarial detection framework for vision sensors pipelines.<n>A SemantiGAN module functions as a multi class semantic discriminator, identifying and filtering visually inconsistent adversarial inputs.<n> Evaluations on the Tiny ImageNet dataset demonstrate the effectiveness of AEGIS.
  arXiv  Detail & Related papers  (2026-06-25T12:03:02Z)
• Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification [52.784239635604735]
  VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images.<n>Existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability.<n>We propose a Causal Bootstrapped Alignment framework that explicitly exploits inherent video priors.
  arXiv  Detail & Related papers  (2026-04-17T02:15:59Z)
• Adversarial Patch Generation for Visual-Infrared Dense Prediction Tasks via Joint Position-Color Optimization [14.358458317718174]
  We propose a joint position-color optimization framework (AP-PCO) for generating adversarial patches in visual-infrared settings.<n>We introduce a crossmodal color adaptation strategy that constrains patch appearance according to infrared grayscale characteristics.<n> experiments on visual-infrared dense prediction tasks demonstrate that the proposed AP-PCO achieves consistently strong attack performance.
  arXiv  Detail & Related papers  (2026-02-27T19:26:17Z)
• Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification [14.343677160918723]
  Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation.<n> estimating reliable cross-modality association is a major challenge in USVI-ReID.<n>This paper focuses on addressing cross-modality learning from two aspects: bias-mitigated global association and modality-invariant representation learning.
  arXiv  Detail & Related papers  (2025-12-08T17:42:28Z)
• TransFIRA: Transfer Learning for Face Image Recognizability Assessment [73.61309363885552]
  TransFIRA is a lightweight and annotation-free framework that grounds recognizability directly in embedding space.<n>New extensions beyond faces include encoder-grounded explainability that reveals how degradations and subject-specific factors affect recognizability.<n> Experiments confirm state-of-the-art results on faces, strong robustness on body recognition, and under cross-dataset shifts.
  arXiv  Detail & Related papers  (2025-10-07T18:16:21Z)
• RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation [67.38036090822982]
  We propose RoboView-Bias, the first benchmark specifically designed to quantify visual bias in robotic manipulation.<n>We create 2,127 task instances that enable robust measurement of biases induced by individual visual factors and their interactions.<n>Our results highlight that systematic analysis of visual bias is a prerequisite for developing safe and reliable general-purpose embodied agents.
  arXiv  Detail & Related papers  (2025-09-26T13:53:25Z)
• Rethinking Evaluation of Infrared Small Target Detection [105.59753496831739]
  This paper introduces a hybrid-level metric incorporating pixel- and target-level performance, proposing a systematic error analysis method, and emphasizing the importance of cross-dataset evaluation.<n>An open-source toolkit has be released to facilitate standardized benchmarking.
  arXiv  Detail & Related papers  (2025-09-21T02:45:07Z)
• Cross-Spectral Body Recognition with Side Information Embedding: Benchmarks on LLCM and Analyzing Range-Induced Occlusions on IJB-MDF [51.36007967653781]
  Vision Transformers (ViTs) have demonstrated impressive performance across a wide range of biometric tasks, including face and body recognition.<n>In this work, we adapt a ViT model pretrained on visible (VIS) imagery to the challenging problem of cross-spectral body recognition.<n>Building on this idea, we integrate Side Information Embedding (SIE) and examine the impact of encoding domain and camera information to enhance cross-spectral matching.<n>Surprisingly, our results show that encoding only camera information - without explicitly incorporating domain information - achieves state-of-the-art performance on the LLCM dataset.
  arXiv  Detail & Related papers  (2025-06-10T16:20:52Z)
• AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives [2.0293118701268154]
  Embodied AI systems are transforming autonomous navigation for ground vehicles and drones by enhancing their perception abilities.<n>We present AetherVision-Bench, a benchmark for multi-angle segmentation across aerial, and ground perspectives.<n>We assess state-of-the-art OVSS models on the proposed benchmark and investigate the key factors that impact the performance of zero-shot transfer models.
  arXiv  Detail & Related papers  (2025-06-04T08:41:19Z)
• Multi-Domain Biometric Recognition using Body Embeddings [51.36007967653781]
  We show that body embeddings perform better than face embeddings in medium-wave infrared (MWIR) and long-wave infrared (LWIR) domains.<n>We leverage a vision transformer architecture to establish benchmark results on the IJB-MDF dataset.<n>We also show that finetuning a body model, pretrained exclusively on VIS data, with a simple combination of cross-entropy and triplet losses achieves state-of-the-art mAP scores.
  arXiv  Detail & Related papers  (2025-03-13T22:38:18Z)
• Self-Supervised Graph Transformer for Deepfake Detection [1.8133635752982105]
  Deepfake detection methods have shown promising results in recognizing forgeries within a given dataset. Deepfake detection system must remain impartial to forgery types, appearance, and quality for guaranteed generalizable detection performance. This study introduces a deepfake detection framework, leveraging a self-supervised pre-training model that delivers exceptional generalization ability.
  arXiv  Detail & Related papers  (2023-07-27T17:22:41Z)
• Causal Effect Estimation with Variational AutoEncoder and the Front Door Criterion [23.20371860838245]
  The front-door criterion is often difficult to identify the set of variables used for front-door adjustment from data. By leveraging the ability of deep generative models in representation learning, we propose FDVAE to learn the representation of a Front-Door adjustment set with a Variational AutoEncoder.
  arXiv  Detail & Related papers  (2023-04-24T10:04:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.