Scalable Framework for Classifying AI-Generated Content Across Modalities
This addresses the need for effective content classification as generative AI evolves, though it appears incremental in its approach.
The paper tackles the problem of distinguishing human from AI-generated content and classifying outputs from different generative models, presenting a scalable framework that achieves high accuracy on text and image classification tasks in evaluations on the Defactify4 dataset.
The rapid growth of generative AI technologies has heightened the importance of effectively distinguishing between human and AI-generated content, as well as classifying outputs from diverse generative models. This paper presents a scalable framework that integrates perceptual hashing, similarity measurement, and pseudo-labeling to address these challenges. Our method enables the incorporation of new generative models without retraining, ensuring adaptability and robustness in dynamic scenarios. Comprehensive evaluations on the Defactify4 dataset demonstrate competitive performance in text and image classification tasks, achieving high accuracy across both distinguishing human and AI-generated content and classifying among generative methods. These results highlight the framework's potential for real-world applications as generative AI continues to evolve. Source codes are publicly available at https://github.com/ffyyytt/defactify4.