arXiv Computer Vision September 18, 2026 By Athanasios Angelakis, Marta Gomez-Barrero

Compact Vision Models for Iris Presentation Attack Detection under Presentation Attack Instrument Shift and Environmental Degradation

Read the original on arXiv Computer Vision →

The paper evaluates three compact computer‑vision models—each with about 0.26 million trainable parameters—for iris presentation attack detection (PAD) under conditions not seen during training, such as new presentation attack instruments (PAIs) and environmental degradation. The models are trained from scratch without external pretraining or data augmentation and tested on the Notre Dame subset of LivDet‑Iris 2017 across known‑attack, unknown‑attack, corrupted, and pooled partitions. Results show significant performance drops when moving from known to unknown attacks, with the best model, ZACH‑ViT, achieving the lowest unknown‑attack APCER (≈47.7 %) and D‑EER (≈38.9 %), yet overall errors remain high enough to preclude deployment readiness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

benchmarks

arXiv AI

Aug 25

A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models

arXiv:2607.27910v2 Announce Type: replace Abstract: Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder...

By Xiangyu Yin, Tora Bodin, Rohan Menon, Chih-Hong Cheng

llms multimodal safety

arXiv Machine Learning

Aug 11

LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection

arXiv:2608. 09633v1 Announce Type: cross Abstract: Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks.

By Peter Lorenz, Anjith George, Marcel S\'ebastien

llms fine-tuning benchmarks

arXiv AI

Aug 17

Beyond aggregate scores: Deployment-aware and non-compensatory benchmarking of vision-based eye-state recognition models for driver monitoring

arXiv:2606. 08123v2 Announce Type: replace-cross Abstract: Model selection for safety-relevant visual recognition is often based on clean aggregate performance, although robustness, transfer, embedded latency, and explanation faithfulness may produce different preferences.

By Ruben Dario Florez-Zela

llms benchmarks safety

arXiv AI

Jun 19

Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

arXiv:2606. 20502v1 Announce Type: cross Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved.

By Arastoo Zibaeirad, Marco Vieira

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 30

Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

arXiv:2607. 26993v1 Announce Type: new Abstract: Face presentation attack detection (PAD) remains challenging under cross-dataset evaluation, where domain shift degrades models trained on a single dataset.

By Peter Lorenz, Anjith George, S\'ebastien Marcel

llms multimodal benchmarks

arXiv Computer Vision

Sep 4

Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision Systems

The paper evaluates six preprocessing defenses against adversarial attacks on depthwise‑separable CNNs, the dominant architecture in edge vision systems, and finds that these defenses consistently fail to recover clean predictions for such models, whereas a residual architecture shows partial recovery. The study reveals that the same preprocessing steps that break clean predictions leave adversarial predictions largely intact, creating a measurable asymmetry that can be exploited for detection without retraining or architectural changes. It also demonstrates that common image quality metrics do not reliably indicate defense effectiveness, highlighting a methodological gap in current evaluation practices.

By Jannatul Masruk Mukta, Rifa Sanjida, Adrita Rahman Tory, Md. Saifur Rahman, Khondokar Fida Hasan

benchmarks safety

One email a morning, machine-written

Related stories

A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models

LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection

Beyond aggregate scores: Deployment-aware and non-compensatory benchmarking of vision-based eye-state recognition models for driver monitoring

Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision Systems