Study: Slanted framing of real images outpaces deepfakes in multimodal misinformation

IAugenstein · x · 2026-09-02

An analysis of 27k posts across 7 languages on X reveals the mechanisms of multimodal misinformation. It finds that slanted framing of real images is more prevalent than deepfakes or doctored images, while vaccine misinformation frequently borrows credibility via news screenshots. The paper introduces a unified taxonomy (MMMMM) and an automated annotation pipeline using Vision-Language Models (VLMs) to validate these insights.

Related event: Study Reveals Miscontextualized Real Images Outpace Deepfakes in Multimodal Misinformation(2 posts)→

Original post →

More from Safety

Safety channel →