Linguistic profiling of deepfakes: An open database for next-Generation deepfake detection

The emergence of text-to-image generative models has revolutionized the field of deepfakes, enabling the creation of realistic and convincing visual content directly from textual descriptions. However, this advancement presents considerably greater challenges in detecting the authenticity of such content. Existing deepfake detection datasets and methods often fall short in effectively capturing the extensive range of emerging deepfakes and offering satisfactory explanatory information for detection. To address the significant issue, this paper introduces a deepfake database (DFLIP-3K) for the development of convincing and explainable deepfake detection. It encompasses about 800K diverse deepfake images synthesized from 3K community checkpoints spanning 27 major base architectures, together with about 700K paired linguistic footprints. In this work, we benchmark architecture-level model identification over the 27 base-architecture classes, while fine-grained checkpoint attribution over thousands of intra-family variants remains an open problem enabled by our metadata release. The two distinguished features enable DFLIP-3K to develop a benchmark that promotes progress in linguistic profiling of deepfakes, which includes three sub-tasks, namely binary AI-generated image detection, model identification, and prompt prediction. The generation model and prompt are two essential components of each deepfake, and thus dissecting them linguistically allows for an invaluable exploration of trustworthy and interpretable evidence in deepfake detection, which we believe is the key to next-generation deepfake detection. Furthermore, DFLIP-3K is envisioned as an open database that fosters transparency and encourages collaborative efforts to further enhance its growth. Our extensive experiments on the developed benchmark verify that our DFLIP-3K database is capable of serving as a standardized resource for evaluating and comparing linguistic-based deepfake detection, identification, and prompt prediction techniques. The project page is https://github.com/iamwangyabin/DFLIP-3K.