Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning
By: Yiheng Li , Zichang Tan , Zhen Lei and more
Potential Business Impact:
Finds fake pictures from new AI tools.
A major struggle for AI-generated image detection is identifying fake images from unseen generators. Existing cutting-edge methods typically customize pre-trained foundation models to this task via partial-parameter fine-tuning. However, these parameters trained on a narrow range of generators may fail to generalize to unknown sources. In light of this, we propose a novel framework named Image-Adaptive Prompt Learning (IAPL), which enhances flexibility in processing diverse testing images. It consists of two adaptive modules, i.e., the Conditional Information Learner and the Confidence-Driven Adaptive Prediction. The former employs CNN-based feature extractors to learn forgery-specific and image-specific conditions, which are then propagated to learnable tokens via a gated mechanism. The latter optimizes the shallowest learnable tokens based on a single test sample and selects the cropped view with the highest prediction confidence for final detection. These two modules enable the prompts fed into the foundation model to be automatically adjusted based on the input image, rather than being fixed after training, thereby enhancing the model's adaptability to various forged images. Extensive experiments show that IAPL achieves state-of-the-art performance, with 95.61% and 96.7% mean accuracy on two widely used UniversalFakeDetect and GenImage datasets, respectively.
Similar Papers
PLA: Prompt Learning Attack against Text-to-Image Generative Models
Cryptography and Security
Makes AI create forbidden pictures.
Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation
CV and Pattern Recognition
Finds hidden problems in factories using smart descriptions.
AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt
CV and Pattern Recognition
Makes AI give wrong answers using fake instructions.