Statistical Signal Amplification for Watermark Verification in Low-Rank Diffusion Adaptations
DOI:
https://doi.org/10.13052/jwe1540-9589.2561Keywords:
Low-Rank Adaptation(LoRA), Diffusion Models, Digital Watermarking, Copyright Protection, Statistical Signal AmplificationAbstract
As the World Wide Web evolves into the central infrastructure for AI-generated content (AIGC), ensuring the provenance of assets distributed via online platforms has become a critical challenge in Web Engineering. The uncontrolled propagation of Low-Rank Adaptation (LoRA) models facilitates unauthorized style mimicry, yet existing watermarks often fail to survive LoRA’s parameter compression. To safeguard digital trust and creator rights, we propose an Adaptation-Agnostic Trace Verification method optimized for secure web ecosystems. Our approach combines deep learning-based watermarking with a Statistical Resonance Amplifier (SRA) to induce the transfer of high-frequency signals into model weights. Furthermore, to overcome the noise limitations of single-image analysis in distributed web applications, we introduce an ensemble-based detection technique. Experimental results validate the method’s robustness, achieving an AUC-ROC of 0.891 even in highly restricted Rank 32 environments (using 100 generated images) and a near-perfect 0.999 at Rank 128, without degrading generation quality. This study presents a practical technology for AI governance and copyright protection, essential for ensuring the trustworthiness of AI-enhanced Web services.
Downloads
References
Liu, Zhenguang, et al. “Harnessing frequency spectrum insights for image copyright protection against diffusion models.” Proceedings of the Computer Vision and Pattern Recognition Conference 2025.
Lin, Dongdong, et al. “An efficient watermarking method for latent diffusion models via low-rank adaptation.” arXiv preprint arXiv:2410.20202 2024.
Cui, Yingqian, et al. “Ft-shield: A watermark against unauthorized fine-tuning in text-to-image diffusion models.” ACM SIGKDD Explorations Newsletter 26.2: 76–88, 2025.
Cao, Huangsen, et al. “HyperDet: Generalizable detection of synthesized images by generating and merging a mixture of hyper LoRAs.” arXiv preprint arXiv:2410.06044 2024.
Wang, Zilan, et al. “Sleepermark: Towards robust watermark against fine-tuning text-to-image diffusion models.” Proceedings of the Computer Vision and Pattern Recognition Conference 2025.
Lv, Peizhuo, et al. “LoRAGuard: An effective black-box watermarking approach for LoRAs.” arXiv preprint arXiv:2501.15478 2025.
Alam, Inzamamul, et al. “SpecGuard: Spectral projection-based advanced invisible watermarking.” Proceedings of the IEEE/CVF International Conference on Computer Vision 2025.
Lee Dae-hee, AI Copyright Lawsuit Analysis: Sarah Andersen v. Stability AI, Korea Copyright Commission, Issue Report 2013-15.
Zhang, Xuanyu, et al. “Editguard: Versatile image watermarking for tamper localization and copyright protection.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024.
Zhong, Haonan, et al. “Copyright protection and accountability of generative ai: Attack, watermarking and attribution.” Companion Proceedings of the ACM Web Conference 2023.
Nguyen, Phuc, et al. “Image copyright protection: A comprehensive survey of digital watermarking, deep learning, and blockchain approaches.” IEEE Open Journal of the Computer Society 7:244–263, 2026.
Jiang, Zhengyuan, et al. “Watermark-based attribution of AI-generated content.” arXiv preprint arXiv:2404.04254 2024.
Zhao, Xuandong, et al. “Invisible image watermarks are provably removable using generative AI.” Advances in Neural Information Processing Systems 37:8643–8672, 2024.
Zhang, Lijun, et al. “Robust image watermarking using stable diffusion.” arXiv preprint arXiv:2401.04247 2024.
Zhang, Lijun, et al. “Attack-resilient image watermarking using stable diffusion.” Advances in Neural Information Processing Systems 37:38480–38507, 2024.
Yang, Zijin, et al. “Gaussian shading: Provable performance-lossless image watermarking for diffusion models.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024.
Fernandez, Pierre, et al. “The stable signature: Rooting watermarks in latent diffusion models.” Proceedings of the IEEE/CVF International Conference on Computer Vision 2023.
