SERUM:一种简单、高效、鲁棒且统一的扩散图像生成标记方法
SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation
AI总结:
SERUM通过在扩散模型生成的初始噪声中添加唯一水印噪声,并训练轻量级检测器识别水印图像,实现了高效且鲁棒的图像标记,同时保持图像质量影响极小。
摘要:
我们提出SERUM:一种简单却高效的扩散模型生成图像标记方法。我们仅在初始扩散生成噪声中添加唯一水印噪声,并训练轻量级检测器来识别水印图像,简化并统一了先前方法的优势。SERUM对任何图像增强或水印移除攻击都具有鲁棒性,并且极其高效,同时对图像质量影响极小。与以往方法相比,后者通常只能抵御有限的扰动,并且训练、注入和检测成本显著。我们的SERUM在大多数情况下在1%的假阳性率下实现了最高的真阳性率,同时具有快速注入和检测以及低检测器训练成本。其解耦架构也无缝支持多个用户,通过嵌入个性化水印并最小化水印之间的干扰。总体而言,我们的方法为标记扩散模型的输出并可靠区分生成图像与自然图像提供了一个实用的解决方案。
英文摘要:
We propose SERUM: an intriguingly simple yet highly effective method for marking images generated by diffusion models (DMs). We only add a unique watermark noise to the initial diffusion generation noise and train a lightweight detector to identify watermarked images, simplifying and unifying the strengths of prior approaches. SERUM provides robustness against any image augmentations or watermark removal attacks and is extremely efficient, all while maintaining negligible impact on image quality. In contrast to prior approaches, which are often only resilient to limited perturbations and incur significant training, injection, and detection costs, our SERUM achieves remarkable performance, with the highest true positive rate (TPR) at a 1% false positive rate (FPR) in most scenarios, along with fast injection and detection and low detector training overhead. Its decoupled architecture also seamlessly supports multiple users by embedding individualized watermarks with little interference between the marks. Overall, our method provides a practical solution to mark outputs from DMs and to reliably distinguish generated from natural images.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。