编辑消除而我的面孔不会保留：针对恶意生成式编辑的个人生物特征防御
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
AI总结：
针对扩散模型恶意肖像编辑威胁，本文提出 FaceLock，通过融合人脸识别与视觉感知优化对抗扰动以破坏生物特征，并在防御效果和抗净化鲁棒性上优于基线。
摘要：
扩散模型的最新进展使生成式图像编辑更易获得，既支持创意编辑，也引发了伦理担忧，尤其是对人类肖像的恶意编辑会威胁隐私和身份安全。现有保护方法主要依赖对抗扰动来使编辑失效，但在面对多样化编辑请求时往往失败。我们提出 FaceLock，这是一种新颖的肖像保护方法，通过优化对抗扰动来破坏或显著改变生物特征信息，使编辑后的输出在生物特征上不可识别。FaceLock 将人脸识别和视觉感知整合到扰动优化中，以针对各种编辑尝试提供鲁棒保护。我们还强调了常用评估指标中的缺陷，并揭示它们如何被操纵，强调需要可靠的保护评估。实验表明，FaceLock 在防御恶意编辑方面优于基线方法，并且对净化技术具有鲁棒性。消融研究证实了其在基于扩散的编辑算法中的稳定性和广泛适用性。我们的工作推进了生物特征防御，并为图像编辑中的隐私保护实践奠定了基础。代码可在 https://github.com/taco-group/FaceLock 获取。
英文摘要：
Recent advancements in diffusion models have made generative image editing more accessible, enabling creative edits but raising ethical concerns, particularly regarding malicious edits to human portraits that threaten privacy and identity security. Existing protection methods primarily rely on adversarial perturbations to nullify edits but often fail against diverse editing requests. We propose FaceLock, a novel approach to portrait protection that optimizes adversarial perturbations to destroy or significantly alter biometric information, rendering edited outputs biometrically unrecognizable. FaceLock integrates facial recognition and visual perception into perturbation optimization to provide robust protection against various editing attempts. We also highlight flaws in commonly used evaluation metrics and reveal how they can be manipulated, emphasizing the need for reliable assessments of protection. Experiments show FaceLock outperforms baselines in defending against malicious edits and is robust against purification techniques. Ablation studies confirm its stability and broad applicability across diffusion-based editing algorithms. Our work advances biometric defense and sets the foundation for privacy-preserving practices in image editing. The code is available at: https://github.com/taco-group/FaceLock.
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。
