Paper Detail
Severyn Shykula, Andrii Yermakov, Ivan Samarskyi, Dmytro Mishkin, Jan Cech, Anastasiia Mishchuk
We introduce DF26, a novel benchmark for detecting AI-generated videos containing fully synthetic clips produced by recent text-to-video and image-to-video models. The videos capture single-person public-speaking scenarios, spanning direct-to-camera recordings, official statements, and studio interviews - 271 real and 2,420 synthetic videos generated by seven modern video models. The study on DF26 shows that human performance in detecting AI-generated videos, as well as state-of-the-art deepfake detectors, is close to random chance. Our results highlight the limitations of current evaluation protocols and motivate the need for benchmarks that explicitly measure robustness to modern generative model distribution shifts.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{shykula2026df26,
title = {DF26: We Cannot Tell Fake From Real Anymore},
author = {Severyn Shykula and Andrii Yermakov and Ivan Samarskyi and Dmytro Mishkin and Jan Cech and Anastasiia Mishchuk},
year = {2026},
abstract = {We introduce DF26, a novel benchmark for detecting AI-generated videos containing fully synthetic clips produced by recent text-to-video and image-to-video models. The videos capture single-person public-speaking scenarios, spanning direct-to-camera recordings, official statements, and studio interviews - 271 real and 2,420 synthetic videos generated by seven modern video models. The study on DF26 shows that human performance in detecting AI-generated videos, as well as state-of-the-art deepfake},
url = {https://huggingface.co/papers/2609.07369},
keywords = {text-to-video, image-to-video, deepfake detectors, generative model distribution shifts, AI-generated videos, huggingface daily},
eprint = {2609.07369},
archiveprefix = {arXiv},
}
{}