A Hybrid Model for Natural Face De-Identiation with Adjustable Privacy

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

doi:10.1109/vcip49819.2020.9301866

Cited by 8 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some more recent image privacy researches focus on changing the identity-related information in images [54]. The main techniques are obfuscation and inpainting.…”

Section: Image Privacy Vs Database Privacymentioning

confidence: 99%

DP-Image: Differential Privacy for Image Data in Feature Space

Liu¹,

Ding²,

Xue³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The excessive use of images in social networks, government databases, and industrial applications has posed great privacy risks and raised serious concerns from the public. Even though differential privacy (DP) is a widely accepted criterion that can provide a provable privacy guarantee, the application of DP on unstructured data such as images is not trivial due to the lack of a clear qualification on the meaningful difference between any two images. In this paper, for the first time, we introduce a novel notion of image aware differential privacy, referred to as DP-image, that can protect user's personal information in images, from both human and AI adversaries. The DP-Image definition is formulated as an extended version of traditional differential privacy, considering the distance measurements between feature space vectors of images. Then we propose a mechanism to achieve DP-Image by adding noise to an image feature vector. Finally, we conduct experiments with a case study on face image privacy. Our results show that the proposed DP-Image method provides excellent DP protection on images, with a controllable distortion to faces.

show abstract

“…Some more recent image privacy researches focus on changing the identity-related information in images [54]. The main techniques are obfuscation and inpainting.…”

Section: Image Privacy Vs Database Privacymentioning

confidence: 99%

DP-Image: Differential Privacy for Image Data in Feature Space

Liu¹,

Ding²,

Xue³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nevertheless, this method applies overly strong obfuscation in processed images which result in heave utility loss. Wen et al 17 also adopts disturbance to obfuscate privacy-sensitive information, but separate images features into identity and nonidentity, and then added noise to the identity vectors to protect image privacy.…”

Section: Image Privacy Protectionmentioning

confidence: 99%

Private‐encoder: Enforcing privacy in latent space for human face images

Zhao

Liu

Zhu

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

The explosive growth of various computer vision technologies generates a tremendous amount of visual data online every day. In addition to bringing convenience and revolutionizing our daily life, image data also reveal a wide range of sensitive information and pose unprecedented privacy leakage risks. Particularly, in the case of photos contain human faces, people can easily access those face images on social media without any consent, and the misuse of personal information could cause serious privacy violation to individuals. Therefore, it is essential to consider sanitizing people's identity information when using images containing human faces. As a result, there has been rapid development in the area of facial anonymization, also called image de-identification. However, due to the emergence of numerous deep-learning based attacks, traditional anonymization methods such as blurring and mosaic are weak and ineffective to protect individual's privacy in face images. To respond to this challenge, this article proposes a novel de-identification method that utilizes a deep neural network. The proposed framework encompasses two modules: encoder network and generator network. The encoder transforms a face image into a high-semantic latent vector of codes, which will be de-identified according to the differential privacy criterion. The generator leverages the unconditional generative adversarial network to synthesize high-quality images based on the modified latent codes from the encoder.Extensive experimental results indicate that our proposed model can protect image privacy while keeping the processed image visual realistic.

show abstract