As facial recognition is increasingly adopted for government and commercial services, its potential misuse has raised serious concerns about privacy and civil rights. To counteract, various anti-facial recognition techniques have been proposed for privacy protection by adversarially perturbing face images, among which generative makeup-based approaches are the most popular. However, these methods, designed primarily to impersonate specific target identities, can only achieve weak dodging success rates while increasing the risk of targeted abuse. In addition, they often introduce global visual artifacts or a lack of adaptability to accommodate diverse makeup prompts, compromising user satisfaction. To address the above limitations, we develop MASQUE, a novel diffusion-based framework that generates localized adversarial makeups guided by user-defined text prompts. Built upon precise null-text inversion, customized cross-attention fusion with masking, and a pairwise adversarial guidance mechanism using images of the same individual, MASQUE achieves robust dodging performance without requiring any external identity. Comprehensive evaluations on open-source facial recognition models and commercial APIs demonstrate that MASQUE significantly improves dodging success rates over all baselines, along with higher perceptual fidelity and stronger adaptability to various text makeup prompts.

翻译：随着人脸识别技术在政府和商业服务中的日益普及，其潜在滥用已引发对隐私和公民权利的严重关切。为应对此问题，学界提出了多种通过对抗性扰动人脸图像以保护隐私的反人脸识别技术，其中基于生成式妆容的方法最为流行。然而，这些主要设计用于模仿特定目标身份的方法，仅能实现较低的躲避成功率，同时增加了针对性滥用的风险。此外，这些方法常引入全局视觉伪影或缺乏适应多样化妆容提示的能力，从而影响用户满意度。为解决上述局限，我们开发了MASQUE——一种基于扩散模型的新型框架，可根据用户定义的文本提示生成局部化的对抗性妆容。该框架基于精确的空文本反转、带掩码的自定义交叉注意力融合，以及使用同一人像图像的成对抗性引导机制，无需任何外部身份信息即可实现鲁棒的躲避性能。在开源人脸识别模型和商业API上的综合评估表明，相较于所有基线方法，MASQUE显著提升了躲避成功率，同时具备更高的感知保真度以及对多样化文本妆容提示的更强适应性。