CORE: Conflict-oriented reasoning for multimodal deepfake detection

Arxiv CS.AI (top papers)

The paper introduces CORE, a method for detecting multimodal fake news by reasoning over conflicts between modalities. It aims to address the threat of generative AI to public trust and social stability.

multimodal

Arxiv CS.AI (top papers)·Jinjie ShenYaxiong WangYujiao WuLechao ChengTianrui HuiNan PuZhihui LiZhun Zhong

8 days ago