用可再生二值掩码保护人脸模板，防逆向重建同时保持识别可用性。
FaceCloak: Learning to Protect Face Templates
- 基于单张人脸生成动态干扰掩码，实时加密模板
- 匹配延迟仅0.28毫秒，模型大小0.57MB，性能优于现有方案
- 适合需要高安全性的生物识别系统部署
生成模型能从编码的人脸模板中重构出与原始人脸高度相似的图像，引发安全与隐私担忧。我们提出 extsc{FaceCloak}，一种神经网络框架，通过生成智能、可再生的二值遮罩来保护人脸模板。该方法在运行时利用单个模板实时合成独特干扰项，主动防御逆向攻击，同时严格保证生物特征可用性与不可关联性。经 extsc{FaceCloak} 加密后的模板可抑制敏感属性，并泛化至新特征提取方法，在生物特征匹配准确率与抗重建攻击能力上均优于领先基线。基于 extsc{FaceCloak} 的匹配推理时间仅为0.28毫秒，模型体积仅0.57兆字节。代码已开源，支持可复现研究。
原文摘要 · Abstract (English)
Generative models can reconstruct face images from encoded representations (templates) bearing remarkable likeness to the original face, raising security and privacy concerns. We present \textsc{FaceCloak}, a neural network framework that protects face templates by generating smart, renewable binary cloaks. Our method proactively thwarts inversion attacks by cloaking face templates with unique disruptors synthesized from a single face template on the fly while provably retaining biometric utility and unlinkability. Our cloaked templates can suppress sensitive attributes while generalizing to novel feature extraction schemes and outperform leading baselines in terms of biometric matching and resiliency to reconstruction attacks. \textsc{FaceCloak}-based matching is extremely fast (inference time =0.28 ms) and light (0.57 MB). We have released our \href{https://github.com/sudban3089/FaceCloak.git}{code} for reproducible research.
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。