TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity
This addresses copyright and authenticity risks for AI-generated content, offering a solution to malicious tampering with generative editing tools, but it is incremental as it builds on existing watermarking and detection techniques.
The paper tackles the problem of verifying authenticity and tracing sources of AI-generated images by proposing a tamper-aware watermarking method that achieves state-of-the-art performance in tampering robustness and localization, with a watermark capacity of 256 bits and lossless generation quality.
AI-generated content (AIGC) enables efficient visual creation but raises copyright and authenticity risks. As a common technique for integrity verification and source tracing, digital image watermarking is regarded as a potential solution to above issues. However, the widespread adoption and advancing capabilities of generative image editing tools have amplified malicious tampering risks, while simultaneously posing new challenges to passive tampering detection and watermark robustness. To address these challenges, this paper proposes a Tamper-Aware Generative image WaterMarking method named TAG-WM. The proposed method comprises four key modules: a dual-mark joint sampling (DMJS) algorithm for embedding copyright and localization watermarks into the latent space while preserving generative quality, the watermark latent reconstruction (WLR) utilizing reversed DMJS, a dense variation region detector (DVRD) leveraging diffusion inversion sensitivity to identify tampered areas via statistical deviation analysis, and the tamper-aware decoding (TAD) guided by localization results. The experimental results demonstrate that TAG-WM achieves state-of-the-art performance in both tampering robustness and localization capability even under distortion, while preserving lossless generation quality and maintaining a watermark capacity of 256 bits. The code is available at: https://github.com/Suchenl/TAG-WM.