SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model

Zhenglin Huang, Jinwei Hu, Xiangtai Li, Yiwei He, Xingyu Zhao Bei Peng, Baoyuan Wu, Xiaowei Huang, Guangliang Cheng

Abstract

The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when shared on social media, can mislead extensive audiences and erode trust in digital content, resulting in severe repercussions. Despite some progress, academia has not yet created a large and diversified deepfake detection dataset for social media, nor has it devised an effective solution to address this issue. In this paper, we introduce the Social media Image Detection dataSet (SID-Set), which offers three key advantages:

1. Extensive volume: Featuring 300K AI-generated/tampered and authentic images with comprehensive annotations.
2. Broad diversity: Encompassing fully synthetic and tampered images across various classes.
3. Elevated realism: Including images that are predominantly indistinguishable from genuine ones through mere visual inspection.

Furthermore, leveraging the exceptional capabilities of large multimodal models, we propose a new image deepfake detection, localization, and explanation framework, named SIDA (Social media Image Detection, localization, and explanation Assistant). SIDA not only discerns the authenticity of images but also delineates tampered regions through mask prediction and provides textual explanations of the model’s judgment criteria. Compared with state-of-the-art deepfake detection models on SID-Set and other benchmarks, extensive experiments demonstrate that SIDA achieves superior performance.

News

• 🔥 The code and dataset are coming soon

Methods

Figure 1: Generation Process

Figure 2: Model Pipeline Overview

Experiment

Citation

@misc{huang2024sidasocialmediaimage,
        title={SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model}, 
        author={Zhenglin Huang and Jinwei Hu and Xiangtai Li and Yiwei He and Xingyu Zhao and Bei Peng and Baoyuan Wu and Xiaowei Huang and Guangliang Cheng},
        year={2024},
        eprint={2412.04292},
        archivePrefix={arXiv},
        primaryClass={cs.CV},
        url={https://arxiv.org/abs/2412.04292}, 
  }

Acknowledgement

• This work is built upon the LLaVA and LISA.