DCT-Shield：一种针对恶意图像编辑的鲁棒频域防御方法
DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editing
AI总结：
针对现有像素空间图像编辑防御方法噪声易察觉、抗JPEG压缩等净化技术鲁棒性差的问题，提出DCT-Shield频域防御方法，通过修改图像DCT系数生成对抗样本，在保障防护效果的同时减少了视觉伪影。
摘要：
扩散模型的发展使得通过文本提示即可轻松完成图像编辑，这引发了人们对图像安全性的担忧。能够获取用户图像的攻击者可利用这类工具实施恶意编辑。近期的防御方法尝试通过在像素空间添加有限噪声来干扰基于扩散的编辑模型的运行，以此保护图像。然而，现有方法添加的对抗噪声很容易被人眼察觉。此外，在可行的像素预算下，这类方法大多对JPEG压缩等净化技术不具备鲁棒性。我们提出了一种全新的优化方法，通过修改输入图像的离散余弦变换（DCT）系数，直接在频域引入对抗扰动。借助JPEG流水线，我们的方法生成的对抗图像可有效阻止恶意图像编辑。在多种任务和数据集上开展的大量实验表明，我们的方法在保持相近编辑防护水平和抗噪声净化技术鲁棒性的同时，引入的视觉伪影更少。
英文摘要：
Advancements in diffusion models have enabled effortless image editing via text prompts, raising concerns about image security. Attackers with access to user images can exploit these tools for malicious edits. Recent defenses attempt to protect images by adding a limited noise in the pixel space to disrupt the functioning of diffusion-based editing models. However, the adversarial noise added by previous methods is easily noticeable to the human eye. Moreover, most of these methods are not robust to purification techniques like JPEG compression under a feasible pixel budget. We propose a novel optimization approach that introduces adversarial perturbations directly in the frequency domain by modifying the Discrete Cosine Transform (DCT) coefficients of the input image. By leveraging the JPEG pipeline, our method generates adversarial images that effectively prevent malicious image editing. Extensive experiments across a variety of tasks and datasets demonstrate that our approach introduces fewer visual artifacts while maintaining similar levels of edit protection and robustness to noise purification techniques.
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。
