Organizing the NTIRE 2026 challenge at CVPR and developing robust, explainable detectors of AI-generated and forged images.
Role: Challenge Organizer, Project Head
Period: Apr 2025 – present
AI-generated image detectors reach near-perfect accuracy on clean benchmarks but lose it under everyday image transformations and deliberate attacks. We developed a testing methodology, collected a large-scale dataset with crowdsourced markup, and built a benchmark of detector robustness.
On this basis we organized the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild at CVPR 2026 — one of the most popular NTIRE challenges, with 511 registered participants and 20 teams submitting final solutions. The challenge dataset contains 108,750 real and 185,750 AI-generated images from 42 generators with 36 types of transformations (Gushchin et al., 2026).
Our team also takes part in related challenges: we proposed a grounded artifact-evidence approach for the Explainable Deepfake Detection Challenge (Filippov et al., 2026) and took third place in the GenText-Forensics challenge at ACM MM 2026 (Koltsov et al., 2026).
Detecting generated content goes hand in hand with assessing it: we proposed TIQA, a human-aligned metric for perceptual quality of text rendered in AI-generated images (Koltsov et al., 2026).
Overview of the NTIRE 2026 challenge on robust AI-generated image detection, held in conjunction with the NTIRE workshop at CVPR 2026. The challenge dataset contains 108,750 real and 185,750 AI-generated images from 42 generators with 36 types of image transformations. 511 participants registered and 20 teams submitted valid final solutions.
@inproceedings{gushchinNtire2026,title={{NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild}},author={Gushchin, Aleksandr and Abud, Khaled and Shumitskaya, Ekaterina and Filippov, Artem and Bychkov, Georgii and Lavrushkin, Sergey and Erofeev, Mikhail and Antsiferova, Anastasia and Chen, Changsheng and Tan, Shunquan and Timofte, Radu and Vatolin, Dmitriy and others},year={2026},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},}
arXiv
MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake Detection
Artem Filippov, Aleksandr Gushchin, Kirill Koltsov, Dmitriy Vatolin, and Anastasia Antsiferova
Our solution for the Explainable Deepfake Detection Challenge at ACM MM 2026: a multi-backbone DINOv3 detector with forensic features, an artifact evidence map trained with weak patch-level supervision, and class-conditional Qwen3-VL explanation generators.
@misc{filippovMsu2026,title={{MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake Detection}},author={Filippov, Artem and Gushchin, Aleksandr and Koltsov, Kirill and Vatolin, Dmitriy and Antsiferova, Anastasia},year={2026},journal={arXiv preprint arXiv:2610.09952},}
arXiv
Team MSU GenText-Forensics Challenge 2026 Technical Report
Kirill Koltsov, Aleksandr Gushchin, Dmitriy Vatolin, and Anastasia Antsiferova
Our solution for the GenText-Forensics challenge at ACM MM 2026, which took third place.
@misc{koltsovGentext2026,title={{Team MSU GenText-Forensics Challenge 2026 Technical Report}},author={Koltsov, Kirill and Gushchin, Aleksandr and Vatolin, Dmitriy and Antsiferova, Anastasia},year={2026},journal={arXiv preprint arXiv:2609.38391},}
ACM MM
TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images
Kirill Koltsov, Aleksandr Gushchin, Dmitriy Vatolin, and Anastasia Antsiferova
In Proceedings of the 34th ACM International Conference on Multimedia, 2026
A human-aligned metric for perceptual quality assessment of text rendered in AI-generated images.
@inproceedings{koltsovTiqa2026,title={{TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images}},author={Koltsov, Kirill and Gushchin, Aleksandr and Vatolin, Dmitriy and Antsiferova, Anastasia},year={2026},booktitle={Proceedings of the 34th ACM International Conference on Multimedia},}