Rethinking Image Editing Detection in the Era of Generative AI Revolution

Zhihao Sun, Haipeng Fang, Juan Cao, Xinying Zhao, Danding Wang

Abstract:

Considering that image editing and manipulation technologies pose significant threats to the authenticity and security of image content, research on image regional manipulation detection has always been a critical issue. The accelerated advancement of generative AI significantly enhances the viability and effectiveness of generative regional editing methods and has led to their gradual replacement of traditional image editing tools or algorithms. However, current research primarily focuses on traditional image tampering, and there remains a lack of a comprehensive dataset containing images edited with abundant and advanced generative regional editing methods.

We endeavor to fill this vacancy by constructing the GRE dataset, a large-scale generative regional editing detection dataset with the following advantages: 1) Integration of a logical and simulated editing pipeline, leveraging multiple large models in various modalities. 2) Inclusion of various editing approaches with distinct characteristics. 3) Provision of comprehensive benchmark and evaluation of SOTA methods across related domains. 4) Analysis of the GRE dataset from multiple dimensions including necessity, rationality, and diversity. Extensive experiments and in-depth analysis demonstrate that this larger and more comprehensive dataset will significantly enhance the development of detection methods for generative editing.

Primary Subject Area: [Generation] Social Aspects of Generative AI

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: Considering the potential risks of multimedia content security posed by generative regional editing and manipulation, we utilize various large models from multiple modalities to construct a high-quality dataset for generative regional editing detection. This dataset facilitates model training and method evaluation in the field of image manipulation detection, particularly in the context of the generative AI revolution. The rich analysis and evaluation experiments demonstrate the new challenges brought by generative models to the domain of image manipulation detection, as well as the role of this dataset in maintaining multimedia content security.

Submission Number: 445