Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Creating Blank Canvas Against AI-enabled Image Forgery

About

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.

Qi Song, Ziyuan Luo, Renjie Wan• 2025

Related benchmarks

TaskDatasetResultRank
Tamper LocalizationColumbia
IoU74
16
Tamper LocalizationCASIA 1+
IoU62
10
Tamper LocalizationIMD 2020
IoU58
10
Tamper LocalizationDSO
IoU55
10
Tamper LocalizationKorus
mIoU27
10
Tamper LocalizationNIST
IoU31
10
Tamper LocalizationSD Inpaint
F1 Score97.2
6
Tamper LocalizationControlNet
F1 Score0.973
6
Tamper LocalizationSDXL
F1 Score97
6
Tamper LocalizationRePaint
F1 Score96.1
6
Showing 10 of 11 rows

Other info

Follow for update