Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage
Text-to-image diffusion models, such as Stable Diffusion, have shown exceptional potential in generating high-quality images. However, recent studies highlight concerns over the use of unauthorized data in training these models, which may lead to intellectual property infringement or privacy violations. A promising approach to mitigate these issues is to apply a watermark to images and subsequently check if generative models reproduce similar watermark features. In this paper, we examine the robustness of various watermark-based protection methods applied to text-to-image models. We observe that common image transformations are ineffective at removing the watermark effect. Therefore, we propose RATTAN, that leverages the diffusion process to conduct controlled image generation on the protected input, preserving the high-level features of the input while ignoring the low-level details utilized by watermarks. A small number of generated images are then used to fine-tune protected models. Our experiments on three datasets and 140 text-to-image diffusion models reveal that existing state-of-the-art protections are not robust against RATTAN.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removal
Box-free model watermarking has gained significant attention in deep neural network (DNN) intellectual property protection due to its model-agnostic nature and its ability to flexibly manage high-entropy image outputs fr…
Image GenerationHide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
Watermarking has emerged as a key defense against the misuse of machine-generated images (MGIs). Yet the robustness of these protections remains underexplored. To reveal the limits of SOTA proactive image watermarking de…
Character-Level Perturbations Disrupt LLM Watermarks
Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal at…
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a secret watermark key. A core security th…
Dual Defense: Adversarial, Traceable, and Invisible Robust Watermarking against Face Swapping
The malicious applications of deep forgery, represented by face swapping, have introduced security threats such as misinformation dissemination and identity fraud. While some research has proposed the use of robust water…
Face SwappingMisinformation