Face Anti-Spoofing

Also known as FAS

Face anti-spoofing studies how to distinguish a live person from attacks such as printed photos, screen replays, masks, and manipulated images or video. Methods use visual evidence of spoof artifacts, sometimes combining it with language, structured attack knowledge, or reasoning models; vision foundation models and prompt tuning are also being explored. Evaluation on benchmarks such as CelebA-Spoof, MSU-MFSD, and UniAttackData includes cross-dataset tests to measure performance on unfamiliar cameras, environments, and attack types. A central challenge is maintaining reliable detection on unseen attacks and domains without sacrificing efficiency or making explanations unsupported by visual evidence.

Latest papers

13 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Printed and Scanned: Exposing the Fragility of Single-Image Morphing Attack Detectors under Print-Scan Degradation
Oct 26, 2026Diogo J. Paulo, Hugo Proença, João C. NevesImage Forgery Detection Face Presentation Attack Detection
University of Beira Interior · NOVA LINCS · IT: Instituto de Telecomunicac¸˜oes
Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing
Aug 18, 2026Fangling Jiang, Qi Li, Bing Liu +4Face Anti-Spoofing Visual Prompt Learning
The First Affiliated Hospital, the School of Computer Science, University of South China, Hengyang, 421001, China · New Laboratory of Pattern Recognition, MAIS, CASIA, Beijing, 100190, China · Department of Computer Science and Engineering, University of California, Merced, CA, 95340, USA
MS-MFAD : Multimodal large language models for Face Anti-spoofing Detection
Aug 18, 2026Xiaoyong Yu, Rongzhen Li, Shuming Shi +1Face Anti-Spoofing Multimodal Large Language Models
Mashang Consumer Finance Co., Ltd., 4th to 8th Floors, Building B2, Yuxing Plaza, No. 52 Huangshan Avenue Middle Section, Chongqing, 401121, Chongqing, China · Huazhong University of Science and Technology, 1037 Luoyu Road, Hongshan District, Wuhan, 430074, Hubei, China
A Combined Feature-Based Framework for Disguise and Spoofing Detection in Face Recognition Systems
Aug 9, 2026Sangiya PararajasinghamFace Anti-Spoofing Face Recognition
University of Colombo School of Computing (UCSC), University of Colombo, Colombo, Sri Lanka
FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing
Jul 29, 2026Hongyang Wang, Yichen Shi, Hongrui Li +3CoT Reasoning Group Relative Policy Optimization
Shijiazhuang Tiedao University · Fudan University · Shanghai Jiao Tong University +2
DINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofing
Jul 23, 2026Pierre Gallin-Martel, Mika Feng, Koichi Ito +1Vision Foundation Model Adaptation Face Presentation Attack Detection
Graduate School of Information Sciences, Tohoku University, Japan
Unified Face Attack Detection via Fine-Grained Semantic Guidance
Jul 9, 2026Ning Jiang, Shijie Yu, Dingheng Zeng +4Image Forgery Detection Face Presentation Attack Detection
School of Software & Microelectronics, Peking University, Beijing, China · Mashang Consumer Finance Co., Ltd., Chongqing, China
On the Study of Biometric Spoofing Detection using Deep Learning
Jun 9, 2026Kumar Kartikey, Nikos KomninosBiometric Identification Face Anti-Spoofing
School of Science and Technology · City St George’s University of London · London EC10V, UK
UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning
May 9, 2026Hongrui Li, Yichen Shi, Hongyang Wang +4Multimodal Reasoning Face Presentation Attack Detection
Shijiazhuang Tiedao University · Shanghai Jiao Tong University · Ningbo Institute of Digital Twin +1
Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofing
Apr 21, 2026Mika Feng, Pierre Gallin-Martel, Koichi Ito +1Vision Foundation Models Domain Generalization
Graduate School of Information Sciences, Tohoku University, Japan
Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion
Apr 10, 2026Seungjin Jung, Yonghyun Jeong, Minha Kim +3Face Anti-Spoofing Domain Generalization
Department of Artificial Intelligence, Chung-Ang University, Seoul, 06974, Korea · Team of Image Vision, Naver Cloud, Seongnam, 13561, Korea · Department of Human-centric AI, Nota AI, Seoul, 06164, Korea +2
From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
Mar 1, 2026Haoyuan Zhang, Keyao Wang, Guosheng Zhang +11Face Presentation Attack Detection Face Anti-Spoofing
SAI, UCAS · MAIS, CASIA · Baidu Inc +2
Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing
May 14, 2025Yingjie Ma, Xun Lin, Zitong Yu +7Cross-Modal Alignment Domain Generalization
College of Computer Science and Software Engineering, Shenzhen University · School of Computing and Information Technology, Great Bay University · The Chinese University of Hong Kong +5

Oct 26, 2026J/K move · Enter open · S save

Printed and Scanned: Exposing the Fragility of Single-Image Morphing Attack Detectors under Print-Scan Degradation

Diogo J. Paulo, Hugo Proença, João C. Neves

University of Beira Interior · NOVA LINCS · IT: Instituto de Telecomunicac¸˜oes

Image Forgery Detection Face Presentation Attack Detection Image Corruption Robustness Face Anti-Spoofing

Open paper AskPDF arXiv

Face morphing attacks, in which the biometric traits of two or more identities are blended into a single face image, pose a severe threat to identity document issuance and automated border control. Consequently, a large body of work has proposed Single-image Morphing Attack Detection (S-MAD) algorithms and benchmarked them on datasets such as SYN-MAD22. However, the majority of these benchmarks operate exclusively in the digital domain, which contrasts with the real-world passport issuance pipeline in some countries, which still requires an applicant-supplied photograph to be printed and subsequently re-scanned before it is embedded in the identity document or fed into an automated verification system. This print-scan step introduces halftoning, resampling, color-space, and sensor noise that are absent from digital pipelines, and may mask the high-frequency artifacts that S-MAD models rely on. In this work, we introduce a print-scan version of the SYN-MAD22 dataset, obtained by printing and re-scanning all bona fide and morphed images at 300 and 600 DPI, and we use it to evaluate eight state-of-the-art S-MAD models trained exclusively on digital data. We additionally repeat the acquisition with a second scanner to assess cross-device robustness. Our results show that detectors that achieve near state-of-the-art performance in the digital domain suffer a more than threefold increase in average equal error rate, with the same qualitative degradation observed across both scanning devices, exposing a critical, previously under-reported gap between digital-benchmark performance and robustness to print-scan degradation.