Saved in:
Bibliographic Details
Main Authors: Balykin, Andrei, Ganiev, Anvar, Kondranin, Denis, Polevoda, Kirill, Liudkevich, Nikolai, Petrov, Artem
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.14980
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913999058108416
author Balykin, Andrei
Ganiev, Anvar
Kondranin, Denis
Polevoda, Kirill
Liudkevich, Nikolai
Petrov, Artem
author_facet Balykin, Andrei
Ganiev, Anvar
Kondranin, Denis
Polevoda, Kirill
Liudkevich, Nikolai
Petrov, Artem
contents Modern face recognition systems remain vulnerable to spoofing attempts, including both physical presentation attacks and digital forgeries. Traditionally, these two attack vectors have been handled by separate models, each targeting its own artifacts and modalities. However, maintaining distinct detectors increases system complexity and inference latency and leaves systems exposed to combined attack vectors. We propose the Paired-Sampling Contrastive Framework, a unified training approach that leverages automatically matched pairs of genuine and attack selfies to learn modality-agnostic liveness cues. Evaluated on the 6th Face Anti-Spoofing Challenge Unified Physical-Digital Attack Detection benchmark, our method achieves an average classification error rate (ACER) of 2.10 percent, outperforming prior solutions. The framework is lightweight (4.46 GFLOPs) and trains in under one hour, making it practical for real-world deployment. Code and pretrained models are available at https://github.com/xPONYx/iccv2025_deepfake_challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14980
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Paired-Sampling Contrastive Framework for Joint Physical-Digital Face Attack Detection
Balykin, Andrei
Ganiev, Anvar
Kondranin, Denis
Polevoda, Kirill
Liudkevich, Nikolai
Petrov, Artem
Computer Vision and Pattern Recognition
Modern face recognition systems remain vulnerable to spoofing attempts, including both physical presentation attacks and digital forgeries. Traditionally, these two attack vectors have been handled by separate models, each targeting its own artifacts and modalities. However, maintaining distinct detectors increases system complexity and inference latency and leaves systems exposed to combined attack vectors. We propose the Paired-Sampling Contrastive Framework, a unified training approach that leverages automatically matched pairs of genuine and attack selfies to learn modality-agnostic liveness cues. Evaluated on the 6th Face Anti-Spoofing Challenge Unified Physical-Digital Attack Detection benchmark, our method achieves an average classification error rate (ACER) of 2.10 percent, outperforming prior solutions. The framework is lightweight (4.46 GFLOPs) and trains in under one hour, making it practical for real-world deployment. Code and pretrained models are available at https://github.com/xPONYx/iccv2025_deepfake_challenge.
title Paired-Sampling Contrastive Framework for Joint Physical-Digital Face Attack Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.14980