# Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models

arXiv: https://arxiv.org/abs/2412.03283 · HTML: https://mlsanity.com/paper/2412.03283/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 37 of its 56 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 30 of 37)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [Fast Sampling of Diffusion Models with Exponential Integrator](https://mlsanity.com/paper/2204.13902/) (2022)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Robust Invisible Video Watermarking with Attention](https://mlsanity.com/paper/1909.01285/) (2019)
- [Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models](https://mlsanity.com/paper/2404.04956/) (2024)
- [Invisible Image Watermarks Are Provably Removable Using Generative AI](https://mlsanity.com/paper/2306.01953/) (2023)
- [Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances](https://mlsanity.com/paper/2410.18775/) (2024)
- [WAVES: Benchmarking the Robustness of Image Watermarks](https://mlsanity.com/paper/2401.08573/) (2024)
- [RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification](https://mlsanity.com/paper/2404.14055/) (2024)
- [Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks](https://mlsanity.com/paper/2310.00076/) (2023)
- [An Undetectable Watermark for Generative Image Models](https://mlsanity.com/paper/2410.07369/) (2024)
- [Leveraging Optimization for Adaptive Attacks on Image Watermarks](https://mlsanity.com/paper/2309.16952/) (2023)

## Built on by (most cited first, 30 of 52)

- [SEAL: Semantic Aware Image Watermarking](https://mlsanity.com/paper/2503.12172/) (2025)
- [Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image](https://mlsanity.com/paper/2504.20111/) (2025)
- [Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models](https://mlsanity.com/paper/2504.15026/) (2025)
- [Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models](https://mlsanity.com/paper/2510.20468/) (2025)
- [First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge](https://mlsanity.com/paper/2508.21072/) (2025)
- [T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models](https://mlsanity.com/paper/2510.22366/) (2025)
- [Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection](https://mlsanity.com/paper/2602.21593/) (2026)
- [Removal Attack and Defense on AI-generated Content Latent-based Watermarking](https://mlsanity.com/paper/2509.11745/) (2025)
- [SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking](https://mlsanity.com/paper/2603.12749/) (2026)
- [WMCopier: Forging Invisible Image Watermarks on Arbitrary Images](https://mlsanity.com/paper/2503.22330/) (2025)
- [NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models](https://mlsanity.com/paper/2510.13793/) (2025)
- [Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey](https://mlsanity.com/paper/2510.02384/) (2025)
- [TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories](https://mlsanity.com/paper/2607.08400/) (2026)
- [Mitigating Watermark Forgery in Generative Models via Randomized Key Selection](https://mlsanity.com/paper/2507.07871/) (2025)
- [SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks](https://mlsanity.com/paper/2601.20310/) (2026)
- [SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark](https://mlsanity.com/paper/2603.29742/) (2026)
- [Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models](https://mlsanity.com/paper/2503.11404/) (2025)
- [Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models](https://mlsanity.com/paper/2506.06018/) (2025)
- [ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering](https://mlsanity.com/paper/2508.06656/) (2025)
- [Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection](https://mlsanity.com/paper/2601.06639/) (2026)
- [Towards Robust Content Watermarking Against Removal and Forgery Attacks](https://mlsanity.com/paper/2604.06662/) (2026)
- [OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization](https://mlsanity.com/paper/2508.21727/) (2025)
- [RAVEN: Erasing Invisible Watermarks via Novel View Synthesis](https://mlsanity.com/paper/2601.08832/) (2026)
- [Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images](https://mlsanity.com/paper/2604.19090/) (2026)
- [Watermarking Should Be Treated as a Monitoring Primitive](https://mlsanity.com/paper/2605.13095/) (2026)
- [MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks](https://mlsanity.com/paper/2509.10766/) (2025)
- [Causal Fingerprints of AI Generative Models](https://mlsanity.com/paper/2509.15406/) (2025)
- [Low-Compute Watermark Removal via Dual-Domain Natural Projection](https://mlsanity.com/paper/2510.07538/) (2025)
- [TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance](https://mlsanity.com/paper/2512.01314/) (2025)
- [On the Robustness of Watermarking for Autoregressive Image Generation](https://mlsanity.com/paper/2604.11720/) (2026)

## Abstract (arXiv)

Integrating watermarking into the generation process of latent diffusion models (LDMs) simplifies detection and attribution of generated content. Semantic watermarks, such as Tree-Rings and Gaussian Shading, represent a novel class of watermarking techniques that are easy to implement and highly robust against various perturbations. However, our work demonstrates a fundamental security vulnerability of semantic watermarks. We show that attackers can leverage unrelated models, even with different latent spaces and architectures (UNet vs DiT), to perform powerful and realistic forgery attacks. Specifically, we design two watermark forgery attacks. The first imprints a targeted watermark into real images by manipulating the latent representation of an arbitrary image in an unrelated LDM to get closer to the latent representation of a watermarked image. We also show that this technique can be used for watermark removal. The second attack generates new images with the target watermark by inverting a watermarked image and re-generating it with an arbitrary prompt. Both attacks just need a single reference image with the target watermark. Overall, our findings question the applicability of semantic watermarks by revealing that attackers can easily forge or remove these watermarks under realistic conditions.