Exposing Text-Image Inconsistency Using Diffusion Models

1 code implementation • 28 Apr 2024 • Mingzhen Huang, Shan Jia, Zhou Zhou, Yan Ju, Jialing Cai, Siwei Lyu

In the battle against widespread online misinformation, a growing problem is text-image inconsistency, where images are misleadingly paired with texts with different intent or meaning.

Misinformation

AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics

1 code implementation • 14 Apr 2023 • Shan Jia, Mingzhen Huang, Zhou Zhou, Yan Ju, Jialing Cai, Siwei Lyu

To achieve this, we propose a new approach that leverages the DALL-E2 language-image model to automatically generate and splice masked regions guided by a text prompt.

Image and Video Forgery Detection Image Generation

GLFF: Global and Local Feature Fusion for AI-synthesized Image Detection

1 code implementation • 16 Nov 2022 • Yan Ju, Shan Jia, Jialing Cai, Haiying Guan, Siwei Lyu

To address this issue, we propose a Global and Local Feature Fusion (GLFF) framework to learn rich and discriminative representations by combining multi-scale global features from the whole image with refined local features from informative patches for AI synthesized image detection.