HYDRO：基于高保真混合扩散与目标导向方法的不可逆人脸去识别
HYDRO: Towards Non-Reversible Face De-Identification Using a High-Fidelity Hybrid Diffusion and Target-Oriented Approach
浏览论文内容
中文总结 AI 辅助
HYDRO结合目标导向模型与扩散过程，通过注入噪声并恢复，实现不可逆的高保真人脸去识别，平均降低85.7%重建攻击成功率。
中文摘要 AI 辅助
目标导向的人脸去识别模型旨在匿名化目标个体在不同图像或视频帧中的身份，使得目标不再能被可靠识别，同时保持视觉数据的关键特征。此类模型通常利用生成式编码器-解码器架构来操纵面部外观，从而产生逼真的高保真去识别结果，同时确保相当的属性保留能力。然而，目标导向模型也存在无意中保留细微身份线索的风险，使其（可能）可逆并易受重建攻击。为解决此问题，本文提出了一种新颖的（鲁棒的）人脸去识别方法，称为HYDRO，它将目标导向模型与专门设计的扩散过程相结合，该过程旨在破坏任何可能允许学习逆转去识别过程的不可感知信息。HYDRO首先对给定人脸图像进行去识别，向去识别结果注入噪声以阻碍重建，然后应用基于扩散的恢复步骤以提高保真度并最小化噪声过程对数据特征的影响。为进一步提高图像保真度并更好地保留注视方向，还引入了一种新颖的眼睛相似性判别器（ESD），并将其纳入HYDRO的训练中。在三个不同数据集上进行的大量定量和定性实验表明，HYDRO展现出最先进的（SOTA）保真度和属性保留能力，同时是唯一能够抵抗重建攻击的目标导向方法。与多个SOTA竞争对手相比，HYDRO平均将重建攻击的成功率降低了85.7%。
英文摘要
Target-oriented face de-identification models aim to anonymize the identity of a target individual across different images or video frames, such that the target can no longer be reliably recognized, while maintaining key characteristics of the visual data. Such models commonly leverage generative encoder-decoder architectures to manipulate facial appearances, enabling them to produce realistic high-fidelity de-identification results, while ensuring considerable attribute-retention capabilities. However, target-oriented models also carry the risk of inadvertently preserving subtle identity cues, making them (potentially) reversible and susceptible to reconstruction attacks. To address this problem, we introduce in this paper a novel (robust) face de-identification approach, called HYDRO, that combines target-oriented models with a dedicated diffusion process specifically designed to destroy any imperceptible information that may allow learning to reverse the de-identification procedure. HYDRO first de-identifies the given face image, injects noise into the de-identification result to impede reconstruction, and then applies a diffusion-based recovery step to improve fidelity and minimize the impact of the noising process on the data characteristics. To further improve image fidelity and better retain gaze directions, a novel Eye Similarity Discriminator (ESD) is also introduced and incorporated it into the training of HYDRO. Extensive quantitative and qualitative experiments on three diverse datasets demonstrate that HYDRO exhibits state-of-the-art (SOTA) fidelity and attribute-retention capabilities, while being the only target-oriented method resilient against reconstruction attacks. In comparison to multiple SOTA competitors, HYDRO reduces the success of reconstruction attacks by 85.7% on average.
