I Know That Person: Generative Full Body and Face De-identification of People in Images

Brkić, Karla; Sikirić, Ivan; Hrkać, Tomislav; Kalafatić, Zoran

doi:10.1109/cvprw.2017.173

Cited by 85 publications

(52 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is a natural tool to synthesize de-identified images. Karlaet al [1] build a GAN-based model to generate full body images for de-identification, but the quality in face areas is not guaranteed. Blaž et al use GAN to synthesize de-identified faces, but still based on the k-same algorithm [20].…”

Section: Related Workmentioning

confidence: 99%

Privacy-Protective-GAN for Privacy Preserving Face De-Identification

Yang

et al. 2019

J. Comput. Sci. Technol.

125

View full text Add to dashboard Cite

Face de-identification has become increasingly important as the image sources are explosively growing and easily accessible. The advance of new face recognition techniques also arises peoples concern regarding the privacy leakage. The mainstream pipelines of face de-identification are mostly based on the k-same framework, which bears critiques of low effectiveness and poor visual quality. In this paper, we propose a new framework called Privacy-Protective-GAN (PP-GAN) that adapts GAN with novel verificator and regulator modules specially designed for the face de-identification problem to ensure generating deidentified output with retained structure similarity according to a single input. We evaluate the proposed approach in terms of privacy protection, utility preservation, and structure similarity. Our approach not only outperforms existing face de-identification techniques but also provides a practical framework of adapting GAN with priors of domain knowledge.

show abstract

Section: Related Workmentioning

confidence: 99%

Privacy-Protective-GAN for Privacy Preserving Face De-Identification

Yang

et al. 2019

J. Comput. Sci. Technol.

125

View full text Add to dashboard Cite

show abstract

“…Much prior work on achieving privacy with such data, especially with images and videos, has relied on domain knowledge and hand-crafted approaches-such as pixelation, blurring, face/object replacement, etc.-to degrade sensitive information [1,2,4,6,13,27]. These methods can be effective in many practical settings when it is clear what to censor, and some variants are even able to make the resulting image look natural and possess chosen attributese.g., replacing faces with generated ones [3,5,17] of different individuals with the same expression, pose, etc. However, we consider the general case when all cues in an image towards the private attribute can not be enumerated, and that an adversary seeking to recover that attribute will learn an estimator specifically for our encoding.…”

Section: Related Workmentioning

confidence: 99%

Learning Privacy Preserving Encodings Through Adversarial Training

Pittaluga

Koppal

Chakrabarti

2019

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pretrained estimator, our goal is that an estimator be unable to learn to accurately predict the private attributes even with knowledge of the encoding function. We use a natural adversarial optimization-based formulation for thistraining the encoding function against a classifier for the private attribute, with both modeled as deep neural networks. The key contribution of our work is a stable and convergent optimization approach that is successful at learning an encoder with our desired properties-maintaining utility while inhibiting inference of private attributes, not just within the adversarial optimization, but also by classifiers that are trained after the encoder is fixed. We adopt a rigorous experimental protocol for verification wherein classifiers are trained exhaustively till saturation on the fixed encoders. We evaluate our approach on tasks of real-world complexity-learning high-dimensional encodings that inhibit detection of different scene categories-and find that it yields encoders that are resilient at maintaining privacy.

show abstract

“…More recently, deep neural networks have been used for face de-ID. The work of [14] uses GANs to generate de-ID faces, which is extended by Karla et al in [6] for full body synthesis. However, the GAN synthesized de-IDed faces suffer from artifacts such as the skin color disparity between the de-IDed face and the surrounding area.…”

Section: Related Workmentioning

confidence: 99%

De-identification Without Losing Faces

Lyu

2019

Proceedings of the ACM Workshop on Information Hiding and Multimedia Security

View full text Add to dashboard Cite

Training of deep learning models for computer vision requires large image or video datasets from real world. Often, in collecting such datasets, we need to protect the privacy of the people captured in the images or videos, while still preserve the useful attributes such as facial expressions. In this work, we describe a new face de-identification method that can preserve essential facial attributes in the faces while concealing the identities. Our method takes advantage of the recent advances in face attribute transfer models, while maintaining a high visual quality. Instead of changing factors of the original faces or synthesizing faces completely, our method use a trained facial attribute transfer model to map non-identity related facial attributes to the face of donors, who are a small number (usually 2 to 3) of consented subjects. Using the donors' faces ensures that the natural appearance of the synthesized faces, while ensuring the identity of the synthesized faces are changed. On the other hand, the FATM blends the donors' facial attributes to those of the original faces to diversify the appearance of the synthesized faces. Experimental results on several sets of images and videos demonstrate the effectiveness of our face de-ID algorithm.

show abstract

I Know That Person: Generative Full Body and Face De-identification of People in Images

Cited by 85 publications

References 20 publications

Privacy-Protective-GAN for Privacy Preserving Face De-Identification

Privacy-Protective-GAN for Privacy Preserving Face De-Identification

Learning Privacy Preserving Encodings Through Adversarial Training

De-identification Without Losing Faces

Contact Info

Product

Resources

About