给照片加不可见噪声，防生成模型盗用人脸身份。
IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
- 用单次前向传播添加不可见对抗噪声保护人脸
- 在多个主流模型上实现跨模型通用防护效果
- 对压缩、缩放等常见图像操作仍保持有效
近期，InstantID 等零样本方法革新了人脸身份保留生成技术。与需多图微调的 DreamBooth 不同，这类方法仅需一张肖像图，通过强大面部编码器提取身份信息，一次推理即可生成保留身份的图像。然而这一便捷性也带来新风险：人脸身份可能被未经授权地用于生成。本文提出 IDProtector，一种对抗噪声编码器，可在单次前向传播中为肖像图添加不可感知的对抗噪声，实现对多种先进编码器方法（如 InstantID、IP-Adapter、PhotoMaker）的通用防护，并具备对 JPEG 压缩、缩放、仿射变换等常见图像操作的鲁棒性。在多样化的肖像数据集与生成模型上的实验表明，IDProtector 能有效泛化至未见过的数据，甚至可抵御闭源专有模型攻击。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。