{"slug": "df26-we-cannot-tell-fake-from-real-anymore", "title": "DF26: We Cannot Tell Fake From Real Anymore", "summary": "Researchers introduced DF26, a new benchmark for detecting AI-generated videos made with recent text-to-video and image-to-video models. The benchmark covers single-person public-speaking scenarios, including direct-to-camera recordings, official statements, and studio interviews, aiming to test how well fake clips can be distinguished from real footage.", "body_md": "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 interv", "url": "https://wpnews.pro/news/df26-we-cannot-tell-fake-from-real-anymore", "canonical_source": "https://aiflash.com/news/116817/", "published_at": "2026-09-10 06:00:10+00:00", "updated_at": "2026-09-10 06:22:01.177411+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "computer-vision", "ai-research"], "entities": ["DF26"], "alternates": {"html": "https://wpnews.pro/news/df26-we-cannot-tell-fake-from-real-anymore", "markdown": "https://wpnews.pro/news/df26-we-cannot-tell-fake-from-real-anymore.md", "text": "https://wpnews.pro/news/df26-we-cannot-tell-fake-from-real-anymore.txt", "jsonld": "https://wpnews.pro/news/df26-we-cannot-tell-fake-from-real-anymore.jsonld"}}