_version_ 1866914510021853184
author Hopf, Benedikt
Timofte, Radu
Qu, Chenfan
Li, Junchi
Wu, Fei
Lu, Dagong
Yao, Mufeng
Xu, Xinlei
Guo, Fengjun
Tang, Yongwei
Yang, Zhiqiang
Wu, Zhiqiang
Seow, Jia Wen
Koay, Hong Vin
Ren, Haodong
Xu, Feng
Chen, Shuai
Le-Phan, Minh-Khoa
Le, Minh-Hoang
Do, Trong-Le
Tran, Minh-Triet
Jian, Chih-Yu
Wang, Yi-Fan
Chen, Bang-Kang
Chao, You-Chen
Lee, Chia-Ming
Yang, Fu-En
Wang, Yu-Chiang Frank
Hsu, Chih-Chung
Negi, Aashish
Sharma, Hardik
Shaily, Prateek
Kumar, Jayant
Chaudhary, Sachin
Dudhane, Akshay
Hambarde, Praful
Shukla, Amit
Peng, Jielun
Wang, Yabin
Li, Yaqi
Liu, Jincheng
Hong, Xiaopeng
Wadhwani, Krish
Fitzpatrick, Liam
Tiwari, Utkarsh
Benjdira, Bilel
Ali, Anas M.
Boulila, Wadii
Quispe, Cristian Lazo
A, Aishwarya
S, Akshara
N, Ashwathi
Tu, Jiachen
Xu, Guoyi
Jiang, Yaoxin
Liu, Jiajia
Shi, Yaokun
author_facet Hopf, Benedikt
Timofte, Radu
Qu, Chenfan
Li, Junchi
Wu, Fei
Lu, Dagong
Yao, Mufeng
Xu, Xinlei
Guo, Fengjun
Tang, Yongwei
Yang, Zhiqiang
Wu, Zhiqiang
Seow, Jia Wen
Koay, Hong Vin
Ren, Haodong
Xu, Feng
Chen, Shuai
Le-Phan, Minh-Khoa
Le, Minh-Hoang
Do, Trong-Le
Tran, Minh-Triet
Jian, Chih-Yu
Wang, Yi-Fan
Chen, Bang-Kang
Chao, You-Chen
Lee, Chia-Ming
Yang, Fu-En
Wang, Yu-Chiang Frank
Hsu, Chih-Chung
Negi, Aashish
Sharma, Hardik
Shaily, Prateek
Kumar, Jayant
Chaudhary, Sachin
Dudhane, Akshay
Hambarde, Praful
Shukla, Amit
Peng, Jielun
Wang, Yabin
Li, Yaqi
Liu, Jincheng
Hong, Xiaopeng
Wadhwani, Krish
Fitzpatrick, Liam
Tiwari, Utkarsh
Benjdira, Bilel
Ali, Anas M.
Boulila, Wadii
Quispe, Cristian Lazo
A, Aishwarya
S, Akshara
N, Ashwathi
Tu, Jiachen
Xu, Guoyi
Jiang, Yaoxin
Liu, Jiajia
Shi, Yaokun
contents Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight image degradation. In addition to weaker degradations that can accidentally occur in the image processing pipeline, there is another risk of malicious deepfakes that specifically introduce degradations, purposefully exploiting the detector's weaknesses in that regard. Here, we present an overview of the NTIRE 2026 Robust Deepfake Detection Challenge, which specifically addresses that problem. Participants were tasked with building a detector that would later be tested on an unknown test-set, which included both common and uncommon degradations of various strengths. With a total number of 337 participants and 57 submissions to the final leaderboard, the first edition of the challenge was well received. To ensure the reliability of the results, participants were given only 24h to complete the test run with no labels provided, limiting the possibility of training on the test data. Furthermore, the top solutions were scored on a private test-set to detect any such overfitting. This report presents the competition setting, dataset preparation, as well as details and performance of methods. Top methods rely on large foundation models, ensembles, and degradation training to combine generality and robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24163
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Robust Deepfake Detection, NTIRE 2026 Challenge: Report
Hopf, Benedikt
Timofte, Radu
Qu, Chenfan
Li, Junchi
Wu, Fei
Lu, Dagong
Yao, Mufeng
Xu, Xinlei
Guo, Fengjun
Tang, Yongwei
Yang, Zhiqiang
Wu, Zhiqiang
Seow, Jia Wen
Koay, Hong Vin
Ren, Haodong
Xu, Feng
Chen, Shuai
Le-Phan, Minh-Khoa
Le, Minh-Hoang
Do, Trong-Le
Tran, Minh-Triet
Jian, Chih-Yu
Wang, Yi-Fan
Chen, Bang-Kang
Chao, You-Chen
Lee, Chia-Ming
Yang, Fu-En
Wang, Yu-Chiang Frank
Hsu, Chih-Chung
Negi, Aashish
Sharma, Hardik
Shaily, Prateek
Kumar, Jayant
Chaudhary, Sachin
Dudhane, Akshay
Hambarde, Praful
Shukla, Amit
Peng, Jielun
Wang, Yabin
Li, Yaqi
Liu, Jincheng
Hong, Xiaopeng
Wadhwani, Krish
Fitzpatrick, Liam
Tiwari, Utkarsh
Benjdira, Bilel
Ali, Anas M.
Boulila, Wadii
Quispe, Cristian Lazo
A, Aishwarya
S, Akshara
N, Ashwathi
Tu, Jiachen
Xu, Guoyi
Jiang, Yaoxin
Liu, Jiajia
Shi, Yaokun
Computer Vision and Pattern Recognition
Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight image degradation. In addition to weaker degradations that can accidentally occur in the image processing pipeline, there is another risk of malicious deepfakes that specifically introduce degradations, purposefully exploiting the detector's weaknesses in that regard. Here, we present an overview of the NTIRE 2026 Robust Deepfake Detection Challenge, which specifically addresses that problem. Participants were tasked with building a detector that would later be tested on an unknown test-set, which included both common and uncommon degradations of various strengths. With a total number of 337 participants and 57 submissions to the final leaderboard, the first edition of the challenge was well received. To ensure the reliability of the results, participants were given only 24h to complete the test run with no labels provided, limiting the possibility of training on the test data. Furthermore, the top solutions were scored on a private test-set to detect any such overfitting. This report presents the competition setting, dataset preparation, as well as details and performance of methods. Top methods rely on large foundation models, ensembles, and degradation training to combine generality and robustness.
title Robust Deepfake Detection, NTIRE 2026 Challenge: Report
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.24163