DiffusionGuard：针对基于扩散模型的恶意图像编辑的鲁棒防御
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
AI总结：
本文提出 DiffusionGuard，通过攻击扩散早期阶段的对抗噪声和掩码增强，防御带掩码等恶意扩散图像编辑，并构建基准验证其低开销、强鲁棒性与可迁移性。
摘要：
扩散模型的最新进展开启了文本引导图像处理的新时代，使用户能够通过简单的文本提示创建逼真的编辑图像。然而，人们对这些方法可能被滥用，尤其是用于制造误导性或有害内容，存在重大担忧。尽管最近通过引入难以察觉的对抗噪声来诱导模型失效的防御策略已展现出潜力，但它们对于更复杂的操作（例如带掩码的编辑）仍然无效。在本文中，我们提出 DiffusionGuard，这是一种鲁棒且有效的防御方法，可抵御基于扩散模型的图像编辑模型进行的未经授权编辑，即使在具有挑战性的设置下也是如此。通过对这些模型的详细分析，我们引入了一种新颖目标函数，用于生成针对扩散过程早期阶段的对抗噪声。该方法显著提高了对抗噪声的效率和有效性。我们还引入了一种掩码增强技术，以增强测试时对各种掩码的鲁棒性。最后，我们提出了一个综合基准，用于评估在现实场景中防范隐私威胁的方法的有效性和鲁棒性。通过大量实验，我们表明，与最强基线相比，我们的方法以更低的计算成本实现了更强的保护和更好的掩码鲁棒性。此外，与所有基线方法相比，我们的方法表现出更优的可迁移性以及对噪声去除技术更好的恢复能力。我们的源代码可在 https://github.com/choi403/DiffusionGuard 公开获取。
英文摘要：
Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. However, there is significant concern about the potential misuse of these methods, especially in creating misleading or harmful content. Although recent defense strategies, which introduce imperceptible adversarial noise to induce model failure, have shown promise, they remain ineffective against more sophisticated manipulations, such as editing with a mask. In this work, we propose DiffusionGuard, a robust and effective defense method against unauthorized edits by diffusion-based image editing models, even in challenging setups. Through a detailed analysis of these models, we introduce a novel objective that generates adversarial noise targeting the early stage of the diffusion process. This approach significantly improves the efficiency and effectiveness of adversarial noises. We also introduce a mask-augmentation technique to enhance robustness against various masks during test time. Finally, we introduce a comprehensive benchmark designed to evaluate the effectiveness and robustness of methods in protecting against privacy threats in realistic scenarios. Through extensive experiments, we show that our method achieves stronger protection and improved mask robustness with lower computational costs compared to the strongest baseline. Additionally, our method exhibits superior transferability and better resilience to noise removal techniques compared to all baseline methods. Our source code is publicly available at https://github.com/choi403/DiffusionGuard.
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。
