Deep Face Swapping via Cross-Identity Adversarial Training

Shu-hui, Yang; Han, Xue; Ling, Jun; Song, Li; Xie, Rong

doi:10.1007/978-3-030-67835-7_7

Cited by 6 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Face swapping In face swapping, the face region in an image is completely replaced with a different face while the other components of the image remain untouched [121]. Face swapping is a well-known form of creating deepfake videos, and various models have been proposed for this task (See [92,116,126,190] for some examples). Since face swapping modifies the whole face not some attributes, it is not considered as a face editing task in this survey.…”

Section: Latent Space Interpolationmentioning

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: Latent Space Interpolationmentioning

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

“…In general, deepfakes created using autoencoder make the swapped face look like the target face and the source face without paying much attention to the difference between the identity of both the source and the target faces. To produce more deep swapped faces, Yang et al [21] combined Cross-identity adversarial in training.…”

Section: Face Swapmentioning

confidence: 99%

A survey of deepfakes in terms of deep learning and multimedia forensics

Hadi

Kadhem²,

Abbas³

2022

IJECE

View full text Add to dashboard Cite

Artificial intelligence techniques are reaching us in several forms, some of which are useful but can be exploited in a way that harms us. One of these forms is called deepfakes. Deepfakes is used to completely modify video (or image) content to display something that was not in it originally. The danger of deepfake technology impact on society through the loss of confidence in everything is published. Therefore, in this paper, we focus on deepfakedetection technology from the view of two concepts which are deep learning and forensic tools. The purpose of this survey is to give the reader a deeper overview of i) the environment of deepfake creation and detection, ii) how deep learning and forensic tools contributed to the detection of deepfakes, and iii) finally how in the future incorporating both deep learning technology and tools for forensics can increase the efficiency of deepfakes detection.

show abstract

“…Anonymizing facial images is a challenging task, which requires a robust model to modify the original face without destroying the existing data distribution. Existing methods [2][3][4][5][6][7][8] aim to remove all the identification information, and then generate a highly realistic face. These techniques reduce the privacy risks of unnecessary identification, but also destroy the convenience and safety for face recognition.…”

Section: Introductionmentioning

confidence: 99%

Identity-Preserving Face Anonymization via Adaptively Facial Attributes Obfuscation

Han

Chen

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

With the popularity of using computer vision technology in monitoring system, there is an increasing societal concern on intruding people's privacy as the captured images/videos may contain identity-related information e.g. people's face. Existing methods on protecting such privacy focus on removing the identity-related information from faces. However, this would weaken the utility of current monitoring system. In this paper, we develop a face anonymization framework that could obfuscate visual appearance while preserving the identity discriminability. The framework is composed of two parts: an identity-aware region discovery module and an identity-aware face confusion module. The former adaptively locates the identity-independent attributes on human faces, and the latter generates the privacy-preserving faces using original faces and discovered facial attributes. To optimize the face generator, we employ a multi-task based loss function, which consists of discriminator loss, identify preserving loss, and reconstruction loss functions. Our model can achieve a balance between recognition utility and appearance anonymizing by modifying different numbers of facial attributes according to pratical demands, and provide a variety of results. Extensive experiments conducted on two public benchmarks Celeb-A and VGG-Face2 demonstrate the effectiveness of our model under distinct face recognition scenarios. CCS CONCEPTS• Computing methodologies → Computer vision; Biometrics; Computer vision representations.

show abstract

Deep Face Swapping via Cross-Identity Adversarial Training

Cited by 6 publications

References 19 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

A survey of deepfakes in terms of deep learning and multimedia forensics

Identity-Preserving Face Anonymization via Adaptively Facial Attributes Obfuscation

Contact Info

Product

Resources

About