CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

Maximov, Maxim; Elezi, Ismail; Leal-Taixé, Laura

doi:10.1109/cvpr42600.2020.00549

Cited by 156 publications

(191 citation statements)

References 19 publications

Supporting

Mentioning

190

Contrasting

Order By: Relevance

“…Conditional GANs were also used by Maximov et al for their Conditional Identity Anonymization GAN model (CIAGAN) [228]. CIAGAN, in essence, implements a face swapping procedure using an encoder-decoder type generator network trained in an adversarial manner.…”

Section: Deep Learning Approachesmentioning

confidence: 99%

Privacy–Enhancing Face Biometrics: A Comprehensive Survey

Meden

Rot

Terhörst

et al. 2021

IEEE Trans.Inform.Forensic Secur.

106

View full text Add to dashboard Cite

Biometric recognition technology has made significant advances over the last decade and is now used across a number of services and applications. However, this widespread deployment has also resulted in privacy concerns and evolving societal expectations about the appropriate use of the technology. For example, the ability to automatically extract age, gender, race, and health cues from biometric data has heightened concerns about privacy leakage. Face recognition technology, in particular, has been in the spotlight, and is now seen by many as posing a considerable risk to personal privacy. In response to these and similar concerns, researchers have intensified efforts towards developing techniques and computational models capable of ensuring privacy to individuals, while still facilitating the utility of face recognition technology in several application scenarios. These efforts have resulted in a multitude of privacy-enhancing techniques that aim at addressing privacy risks originating from biometric systems and providing technological solutions for legislative requirements set forth in privacy laws and regulations, such as GDPR. The goal of this overview paper is to provide a comprehensive introduction into privacy-related research in the area of biometrics and review existing work on Biometric Privacy-Enhancing Techniques (B-PETs) applied to face biometrics. To make this work useful for as wide of an audience as possible, several key topics are covered as well, including evaluation strategies used with B-PETs, existing datasets, relevant standards, and regulations and critical open issues that will have to be addressed in the future.

show abstract

Section: Deep Learning Approachesmentioning

confidence: 99%

Privacy–Enhancing Face Biometrics: A Comprehensive Survey

Meden

Rot

Terhörst

et al. 2021

IEEE Trans.Inform.Forensic Secur.

106

View full text Add to dashboard Cite

show abstract

“…Gafni et al [12] proposed live face de-identification. Maximov et al [32] proposed CIAGAN by mixing the landmark identity and the desired identity. Zhu et al [55] employed DeepFake for de-identification, but it may require repeated training to swap each pair of identities.…”

Section: Related Workmentioning

confidence: 99%

“…To deal with the privacy concerns, some entities may set up new laws or even remove privacy sensitive image datasets [3,32]. But, this would raise the difficulty for researchers to perform data analysis, like the video recording for diagnosis on the Parkinson's disease.…”

Section: Introductionmentioning

confidence: 99%

“…And the unnatural image may also arouse the curiosity of observers to reveal the real identity of a person [33,36], which may bring about re-identification risks. There are also some recent attempts to synthesize faces based on generative adversarial network (GAN) [12,21,29,32,38,45,55]. But, their results are still unsatisfactory because they cannot achieve a good balance between data privacy and reusability.…”

Section: Introductionmentioning

confidence: 99%

“…DeIdGAN leverages the merits of both the classical k-anonymity method [35,40,48] and the latest deep generative method [13,21,22,27,38] to realize effective face anonymization and it is quite different from the existing de-identification methods. First, compared with state-of-the-art methods [12,29,32,45], DeIdGAN employs a more effective GAN model by taking the shape and style information as input to jointly determine the identity of the synthesized face as well as its outlook (see Figure 1). Second, DeIdGAN relies on a more secure de-identification strategy by anonymizing the input first and then impose additional identity-adversarial constrains to prevent synthesizing sensitive identities.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Effective De-identification Generative Adversarial Network for Face Anonymization

Kuang

Liu

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

The growing application of face images and modern AI technology has raised another important concern in privacy protection. In many real scenarios like scientific research, social sharing and commercial application, lots of images are released without privacy processing to protect people's identity. In this paper, we develop a novel effective de-identification generative adversarial network (DeIdGAN) for face anonymization by seamlessly replacing a given face image with a different synthesized yet realistic one. Our approach consists of two steps. First, we anonymize the input face to obfuscate its original identity. Then, we use our designed deidentification generator to synthesize an anonymized face. During the training process, we leverage a pair of identity-adversarial discriminators to explicitly constrain identity protection by pushing the synthesized face away from the predefined sensitive faces to resist re-identification and identity invasion. Finally, we validate the effectiveness of our approach on public datasets. Compared with existing methods, our approach can not only achieve better identity protection rates but also preserve superior image quality and data reusability, which suggests the state-of-the-art performance. CCS CONCEPTS• Security and privacy → Privacy protections; • Computing methodologies → Computer vision.

show abstract

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

Zhao

Liu

Zhu

et al. 2021

Concurrency and Computation

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

CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

Cited by 156 publications

References 19 publications

Privacy–Enhancing Face Biometrics: A Comprehensive Survey

Privacy–Enhancing Face Biometrics: A Comprehensive Survey

Effective De-identification Generative Adversarial Network for Face Anonymization

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

Contact Info

Product

Resources

About