Welcome to the 6th Face Anti-Spoofing Workshop:
Unified Physical-Digital Attacks Detection@ICCV2025
Afternoon, 19 October, 2025 ICCV
Welcome to the 6th Face Anti-Spoofing Workshop:
Unified Physical-Digital Attacks Detection@ICCV2025
Afternoon, 19 October, 2025 ICCV
The 6th Face Anti-Spoofing Workshop: Unified Physical-Digital Attacks Detection@ICCV2025
Introduction
In recent years, the growing sophistication of face spoofing techniques has significantly threatened the security of face recognition systems. Face Anti-Spoofing (FAS) has thus become a critical component in ensuring the reliability of biometric authentication. To stimulate research in this area, we have organized five successful editions of the Face Anti-Spoofing Workshop and Challenge at major conferences, including CVPR 2019, CVPR 2020, ICCV 2021, CVPR 2023, and CVPR 2024, attracting over 1,400 participating teams from academia and industry. However, unified detection of both physical and digital attacks remains a major challenge. While physical presentation attacks such as print, replay, and 3D mask attacks typically introduce artifacts like color distortion and moiré patterns, digital forgeries—including identity manipulations, adversarial examples, and GAN-based generation—alter facial imagery at the pixel level in often imperceptible ways. Existing solutions still treat these as separate tasks, hindering the development of generalizable models. To address this gap, the 6th Face Anti-Spoofing Workshop@ICCV 2025 introduces the task of Unified Physical-Digital Attack Detection and releases a significantly expanded dataset, UniAttackData+. We collected data from 2,875 participants representing three distinct ethnic groups (i.e., African, East Asian, and Central Asian), capturing 18,250 authentic videos under various lighting conditions, backgrounds, and acquisition devices. For each participant, we applied 54 different attack methods, including 14 physical attacks and 40 digital attacks, resulting in a total of 679,097 forged videos.
Challenge website: [Link]
Workshop Paper Submission Link: Waiting for opening......
Ref:
[1] Ajian Liu, Haocheng Yuan, Xiao Guo, Hui Ma, Wanyi Zhuang, Changtao Miao, Jun Lan, Qi Chu, Jun Wan, Xiaoming Liu, Zhen Lei Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning. [Link]
Workshop Schedule
Date: Oct. 19th, 2025
Current Start Time: October 19, 2025 at 01:00 PM HST ——Current End Time: October 19, 2025 at 05:00 PM HST
13:00 – 13:20 Opening & Workshop Overview (host: organizing units, partners, dataset, competition, and results)
13:20 – 14:00 Keynote Speaker Xiaochun Cao: Talk + Q&A (40 min)
14:00 – 14:25 Tencent Youtu: Presentation + Q&A + Award (25 min)
14:25 – 15:05 Keynote Speaker Zhen Lei: Talk + Q&A (40 min)
15:05 – 15:30 TeleAI: Presentation + Q&A + Award (25 min)
15:30 – 15:40 Coffee Break (10 min)
15:40 – 16:20 Keynote Speaker Yu Yi: Talk + Q&A (40 min)
16:20 – 16:45 Akuvox: Presentation + Q&A + Award (25 min)
16:45 – 17:00 Closing Remarks & Future Work (host, 15 min)
Important Competition Dates:
20 May 2025: Quantitative competition begins; Development data released: training set with true labels; Validation data released: validation set without true labels; Encrypted test data released (no labels provided).
12 June 2025: Release of encrypted final evaluation data (test data without true labels); True labels of validation set released.
13 June 2025: Release of final evaluation data decryption key; Participants start predicting results on the final evaluation data.
28 June 2025: Quantitative competition ends; Deadline for submitting final predictions on test data; Deadline for code submission (organizers verify code on test data).
30 June 2025: Challenge results officially released.
9 July 2025: Deadline for workshop paper submissions.
11 July 2025: Deadline for authors to submit meta-data of accepted papers.
18 August 2025: Camera-ready paper submission deadline.
19 October 2025: Workshop@ICCV 2025 held; Challenge results announced; Award ceremony conducted.
Keynote Speakers:
Xiaochun Cao is the Dean of the School of Cyber Science and Technology at Sun Yat-sen University. His research interests span artificial intelligence, with a particular focus on computer vision and cyber content analysis. He received his B.E. and M.E. degrees in Computer Science from Beihang University (BUAA), China, and his Ph.D. in Computer Science from the University of Central Florida, USA, where his dissertation was nominated for the university-level Outstanding Dissertation Award. After graduation, he worked as a Research Scientist at ObjectVideo Inc. for three years before serving as a Professor at the Institute of Information Engineering, Chinese Academy of Sciences. Dr. Cao has authored or co-authored more than 300 journal and conference papers. He is a two-time recipient of the Piero Zamperoni Best Student Paper Award at the International Conference on Pattern Recognition (2004, 2010). He has also received the Excellent Young Scientists Fund (2014) and the Outstanding Young Scientists Fund (2020) from the National Natural Science Foundation of China. He currently serves on the editorial boards of IEEE TPAMI, IEEE TIP, IEEE TMM, and Acta Electronica Sinica, and was previously an Associate Editor of IEEE TCSVT. Dr. Cao has an outstanding record of mentoring. Several of his Ph.D. students have received prestigious honors, including the Excellent Young Scientists Fund of NSFC, the National High-level Talent Program, and the CCF/CIE/CAS Doctoral Dissertation Awards.
Zhen Lei is an IEEE Fellow and IAPR Fellow, and a Professor at the Institute of Automation, Chinese Academy of Sciences (CASIA) as well as the School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS). His research interests include biometrics, intelligent video analysis, and foundational theories of artificial intelligence. He has led and participated in major national projects, including the National Key R&D Program and the National Natural Science Foundation of China. Dr. Lei has published over 200 papers in top journals and conferences, including 9 IEEE TPAMI papers and more than 60 CCF-A conference papers. He has received four best paper/best student paper awards at flagship conferences and won first prizes in seven international vision competitions. He holds over 30 invention patents, and has contributed to the development of two national standards and seven industry standards. His work has been cited over 32,000 times, with an H-index of 85. He was recognized as an Elsevier Highly Cited Researcher in China (2020–2023) and ranks among the top 2% of scientists globally. His honors include the 2019 IAPR Young Biometrics Researcher Award, Second Prize of the 2019 National Science and Technology Progress Award, First Prize of the 2021 CIE Technology Invention Award, and Second Prize of the 2022 CSIG Natural Science Award. He has also received the Outstanding Contribution Award for the Beijing Olympic and Paralympic Games, the Barcelona Global Smart City Project Nomination Award, and the Huawei Outstanding Technical Collaboration Achievement Award (2020).
Yiyu is currently a Postdoctoral Research Fellow at Nanyang Technological University (NTU), Singapore, working with Prof. Xudong Jiang. He received his Ph.D. from NTU in 2025, under the supervision of Prof. Alex C. Kot, Prof. Yap-Peng Tan, and Prof. Shijian Lu. Prior to that, he earned an M.S. in Machine Learning & Data Science from the University of California, San Diego (2020) and a B.E. in Automation from Tsinghua University (2019). His research focuses on trustworthy machine learning and AI security, aiming to enhance the security and privacy of AI methods throughout their full life cycle. His work covers adversarial attacks, backdoor attacks, and data poisoning (unlearnable examples) along with their mitigation strategies. Recently, his interests have expanded to data privacy protection (e.g., preventing unauthorized commercial use of data and mitigating model inversion risks) and the security of foundation models, including large language models and multimodal systems.
Organizers:
Jun Wan (万军 Primary Contact), Institute of Automation, Chinese Academy of Sciences (CASIA), China, jun.wan@ia.ac.cn
Jiankang Deng, Insightface, jiankangdeng@gmail.com
Jun Lan, Ant Group, China, yelan.lj@antgroup.com
Weiqiang Wang, Ant Group, China, weiqiang.wwq@antgroup.com
Sergio Escalera, Computer Vision Center (UAB) and University of Barcelona, Spain, sergio@maia.ub.es
Hugo Jair Escalante, INAOE, ChaLearn, Mexico, hugojair@inaoep.mx
Xiaoming Liu, Michigan State University (MSU), USA, liuxm@msu.edu
Ajian Liu, Institute of Automation, Chinese Academy of Sciences (CASIA), China, ajian.liu@ia.ac.cn
Zhen Lei, Institute of Automation, Chinese Academy of Sciences (CASIA), China, zhen.lei@ia.ac.cn
Isabelle Guyon, Université Paris-Saclay, France and ChaLearn, Berkeley, California, USA, guyon@chalearn.org
Organizers Institutions: