Creating Blank Canvas Against AI-enabled Image Forgery
This addresses the risk of image forgery for users and platforms, but it is incremental as it builds on existing SAM capabilities with a novel optimization strategy.
The paper tackles the problem of detecting AI-enabled image forgeries by transforming images into a 'blank canvas' using adversarial perturbations on the Segment Anything Model (SAM), achieving effective tamper localization as demonstrated in experiments.
AIGC-based image editing technology has greatly simplified the realistic-level image modification, causing serious potential risks of image forgery. This paper introduces a new approach to tampering detection using the Segment Anything Model (SAM). Instead of training SAM to identify tampered areas, we propose a novel strategy. The entire image is transformed into a blank canvas from the perspective of neural models. Any modifications to this blank canvas would be noticeable to the models. To achieve this idea, we introduce adversarial perturbations to prevent SAM from ``seeing anything'', allowing it to identify forged regions when the image is tampered with. Due to SAM's powerful perceiving capabilities, naive adversarial attacks cannot completely tame SAM. To thoroughly deceive SAM and make it blind to the image, we introduce a frequency-aware optimization strategy, which further enhances the capability of tamper localization. Extensive experimental results demonstrate the effectiveness of our method.