IDProtector：一种用于防御身份保持图像生成的对抗性噪声编码器
IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
AI总结：
本文提出IDProtector对抗性噪声编码器，通过单次前向传播向人像施加不可察觉噪声，以抵御InstantID等基于编码器的身份保持生成，并具备对常见图像变换的鲁棒性和对未知模型及闭源模型的泛化能力。
摘要：
近年来，像 InstantID 这样的零样本方法已经彻底改变了身份保持生成。与 DreamBooth 等多图像微调方法不同，这些零样本方法利用强大的人脸编码器从单张人像照片中提取身份信息，从而通过一次推理即可实现高效的身份保持生成。然而，这种便利性也给面部身份保护带来了新的威胁。本文旨在保护人像照片免受未经授权的基于编码器的定制化使用。我们提出了 IDProtector，这是一种对抗性噪声编码器，能够在单次前向传播中向人像照片施加难以察觉的对抗性噪声。我们的方法能够为肖像提供通用保护，抵御多种最先进的基于编码器的方法，包括 InstantID、IP-Adapter 和 PhotoMaker，同时确保对常见图像变换（如 JPEG 压缩、缩放和仿射变换）的鲁棒性。在多样化的人像数据集和生成模型上的实验表明，IDProtector 能够有效泛化到未见过的数据，甚至包括闭源专有模型。
英文摘要：
Recently, zero-shot methods like InstantID have revolutionized identity-preserving generation. Unlike multi-image finetuning approaches such as DreamBooth, these zero-shot methods leverage powerful facial encoders to extract identity information from a single portrait photo, enabling efficient identity-preserving generation through a single inference pass. However, this convenience introduces new threats to the facial identity protection. This paper aims to safeguard portrait photos from unauthorized encoder-based customization. We introduce IDProtector, an adversarial noise encoder that applies imperceptible adversarial noise to portrait photos in a single forward pass. Our approach offers universal protection for portraits against multiple state-of-the-art encoder-based methods, including InstantID, IP-Adapter, and PhotoMaker, while ensuring robustness to common image transformations such as JPEG compression, resizing, and affine transformations. Experiments across diverse portrait datasets and generative models reveal that IDProtector generalizes effectively to unseen data and even closed-source proprietary models.
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。
