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

TL;DR

This paper introduces SIDA, a multimodal model for detecting, localizing, and explaining deepfakes on social media, supported by a large, diverse, and realistic dataset called SID-Set.

Contribution

The paper presents a new large-scale dataset SID-Set and a multimodal framework SIDA for deepfake detection, localization, and explanation, advancing current capabilities in social media image authenticity assessment.

Findings

SIDA outperforms existing models on SID-Set and other benchmarks.

SID-Set contains 300K diverse, realistic images with comprehensive annotations.

SIDA provides detection, localization, and textual explanations of deepfakes.

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, and (3) elevated realism, with 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 among diversified settings. The code, model, and dataset will be released.