当前位置: X-MOL 学术IEEE Trans. Pattern Anal. Mach. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
On the Reconstruction of Face Images from Deep Face Templates.
IEEE Transactions on Pattern Analysis and Machine Intelligence ( IF 23.6 ) Pub Date : 2018-04-16 , DOI: 10.1109/tpami.2018.2827389
Guangcan Mai , Kai Cao , Pong C Yuen , Anil K Jain

State-of-the-art face recognition systems are based on deep (convolutional) neural networks. Therefore, it is imperative to determine to what extent face templates derived from deep networks can be inverted to obtain the original face image. In this paper, we study the vulnerabilities of a state-of-the-art face recognition system based on template reconstruction attack. We propose a neighborly de-convolutional neural network (NbNet) to reconstruct face images from their deep templates. In our experiments, we assumed that no knowledge about the target subject and the deep network are available. To train the NbNet reconstruction models, we augmented two benchmark face datasets (VGG-Face and Multi-PIE) with a large collection of images synthesized using a face generator. The proposed reconstruction was evaluated using type-I (comparing the reconstructed images against the original face images used to generate the deep template) and type-II (comparing the reconstructed images against a different face image of the same subject) attacks. Given the images reconstructed from NbNets, we show that for verification, we achieve TAR of 95.20 percent (58.05 percent) on LFW under type-I (type-II) attacks @ FAR of 0.1 percent. Besides, 96.58 percent (92.84 percent) of the images reconstructed from templates of partition fa (fb) can be identified from partition fa in color FERET. Our study demonstrates the need to secure deep templates in face recognition systems.

中文翻译:

从深度面部模板重建面部图像。

最新的人脸识别系统基于深度(卷积)神经网络。因此,必须确定从深度网络派生的面部模板可以在多大程度上反转以获得原始面部图像。在本文中,我们研究了基于模板重构攻击的最新人脸识别系统的漏洞。我们提出了一种近邻反卷积神经网络(NbNet),以从其深层模板中重建人脸图像。在我们的实验中,我们假设没有关于目标主题和深度网络的知识。为了训练NbNet重建模型,我们增加了两个基准面部数据集(VGG-Face和Multi-PIE),并使用面部生成器合成了大量图像。使用I型(将重建的图像与用于生成深层模板的原始面部图像进行比较)和II型(将重建的图像与相同对象的不同面部图像进行比较)攻击来评估建议的重建。鉴于从NbNets重建的图像,我们表明,为进行验证,在I型(II型)攻击下,LFW的TAR值为95.20%(58.05%),FAR为0.1%。此外,从分区fa(fb)的模板重建的图像中,有96.58%(92.84%)可以从FERET颜色的fa分区中识别出来。我们的研究表明需要保护面部识别系统中的深层模板。
更新日期:2019-04-03
down
wechat
bug