Personalized and Invertible Face De-identification by Disentangled Identity Information Manipulation

Cao, Junyan; Liu, Bo; Wen, Yunqian; Xie, Rong; Song, Li

doi:10.1109/iccv48922.2021.00332

Cited by 55 publications

(31 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) De-identification: The goal of face de-identification is to remove the identity of a face in a photo or video in order to preserve the privacy of individuals while the other attributes (e.g. sex, age, pose, expression, and illumination) remain unchanged [12]. For example, though collecting huge datasets of images or videos in the wild is a necessary step in most of the computer vision tasks, protecting the privacy of the people captured in these images/videos is indispensable too.…”

Section: A Face Recognitionmentioning

confidence: 99%

A comprehensive survey on semantic facial attribute editing using generative adversarial networks

Nickabadi¹,

Fard²,

Farid³

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: A Face Recognitionmentioning

confidence: 99%

A comprehensive survey on semantic facial attribute editing using generative adversarial networks

Nickabadi¹,

Fard²,

Farid³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…Pan et al 42 proposed a Multi‐factor Modifier (MfM) based on conditional encoder and decoder framework, which achieves multi‐factor facial de/re‐identification. Based on a deep generative model, a personalized and reversible de‐identification method was designed in Reference 43 to control the direction and degree of identity change by introducing a user‐specific password and an adjustable parameter. You et al 44 proposed a reversible privacy protection framework with an encoder and decoder using U‐Net architecture to generate high‐quality protected images without visible facial features.…”

Section: Related Workmentioning

confidence: 99%

“…To achieve a good trade-off between privacy and accessibility for face de-identification, reversible privacy protection has been studied in the literature. [42][43][44] Pan et al 42 proposed a Multi-factor Modifier (MfM) based on conditional encoder and decoder framework, which achieves multi-factor facial de/re-identification. Based on a deep generative model, a personalized and reversible de-identification method was designed in Reference 43…”

Section: Related Workmentioning

confidence: 99%

Face image de‐identification by feature space adversarial perturbation

Xue

Liu

Yuan

et al. 2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Privacy leakage in images attracts increasing concerns these days, as photos uploaded to large social platforms are usually not processed by proper privacy protection mechanisms. Moreover, with advanced artificial intelligence (AI) tools such as deep neural network (DNN), an adversary can detect people's identities and collect other sensitive personal information from images at an unprecedented scale. In this paper, we introduce a novel face image de‐identification framework using adversarial perturbations in the feature space. Manipulating the feature space vector ensures the good transferability of our framework. Moreover, the proposed feature space adversarial perturbation generation algorithm can successfully protect the identity‐related information while ensuring the other attributes remain similar. Finally, we conduct extensive experiments on two face image datasets to evaluate the performance of the proposed method. Our results show that the proposed method can generate real‐looking privacy‐preserving images efficiently. Although our framework has only been tested on two real‐life face image datasets, it can be easily extended to other types of images.

show abstract

“…anonymization [53]- [55] and face swapping [46]- [48] are beyond the scope of FAM. 2) Image quality enhancement: Although the prior knowledge of facial biometrics is widely incorporated when improving the quality of portrait images, such as in image super-resolution [56]- [58] or image restoration [59], images are translated in terms of the quality of textural details or overall perception, which are not considered as facial attributes.…”

Section: Facial Attribute Manipulationmentioning

confidence: 99%

GAN-Based Face Attribute Editing

Liu

Cao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Recently, a variety of methods using the Generative Adversarial Network (GAN) for face editing have been proposed. However, the existing methods cannot control the editing content of the face elements according to the user-specified attributes or need to train a conditional GAN for editing tasks, which means it is difficult to add new attributes in the future. In this paper, a method to edit face attributes by editing the latent variable with the help of a pre-trained unconditional GAN and a linear classification model is proposed. In particular, face attribute editing is divided into two separate stages: Firstly, based on the optimization function, the generative model does a latent variable search to generate a high-quality face image that is similar to the input image. Secondly, by editing the latent variable of the GAN, the attribute of the generated face image can be modified indirectly, so it is almost unaffected by the training process and network structure of GAN, which means it is a flexible method for nearly all GAN network. Images of the FFHQ dataset are edited by attribute labels defined in Celeba dataset for experiments. These experiments prove that our method can edit a variety of face images that vary with race, gender, age, and camera shooting angle. The overall quality of the edited image is not inferior to the other face attribute editing method, and attribute classification for edited image shows a 92.6% attribute editing success rate of the proposed method.

show abstract

Personalized and Invertible Face De-identification by Disentangled Identity Information Manipulation

Cited by 55 publications

References 18 publications

A comprehensive survey on semantic facial attribute editing using generative adversarial networks

A comprehensive survey on semantic facial attribute editing using generative adversarial networks

Face image de‐identification by feature space adversarial perturbation

GAN-Based Face Attribute Editing

Contact Info

Product

Resources

About