Biometric Systems De-Identification: Current Advancements and Future Directions

Shopon,; Tumpa, Sanjida Nasreen; Bhatia, Yajurv; Kumar, Koushal; Gavrilova, Marina L.

doi:10.3390/jcp1030024

Cited by 13 publications

(10 citation statements)

References 114 publications

(134 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, traditional de-identification methods often result in losing essential attributes, such as emotions, which play a fundamental role in human behavior and have significant implications in psychology, psychiatry, and neuroscience. Traditional de-identification methods can be broadly categorized into complete de-identification, soft biometrics de-identification, and traditional biometric preserving de-identification [20]. Fig.…”

Section: Literature Reviewmentioning

confidence: 99%

Emotion-Aware Face De-identification with Generative Adversarial Networks

Shopon,

Gavrilova

2024

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents an innovative end-to-end emotion-preserving de-identification approach utilizing a Generative Adversarial Network (GAN), employing the StyleGAN architecture. The method produces natural-looking de-identified images by generating a synthetic face image dataset and utilizing the DeepFace model for gender classification and representative image selection. An enhanced SimSwap framework enhances emotion preservation, accompanied by a novel loss function tailored to emotional expression preservation. The deep face model serves to classify and recognize emotional expressions in both original and de-identified swapped images. Explicit preservation of emotional expressions during face-swapping is achieved through attribute preservation loss minimization. The paper conducts a detailed ablation study to demonstrate the superiority of the proposed GAN components. The method exhibits superior performance in accuracy and emotion preservation compared to recent face de-identification methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Emotion-Aware Face De-identification with Generative Adversarial Networks

Shopon,

Gavrilova

2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, some researchers have proposed imperceptible face protection methods. [8][9][10][11] These methods aim to synthesize the face protection images that are visually almost identical to the source face images while evading FR systems recognition, as shown in Figure 1. During this process, users only need to simply modify their face images without considering the settings of other factors.…”

Section: F I G U R Ementioning

confidence: 99%

“…Recently, some researchers have proposed imperceptible face protection methods 8‐11 . These methods aim to synthesize the face protection images that are visually almost identical to the source face images while evading FR systems recognition, as shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

AEGAN: Generating imperceptible face synthesis via autoencoder‐based generative adversarial network

Che

Yang

Guo

et al. 2023

Computer Animation & Virtual

View full text Add to dashboard Cite

Face recognition (FR) systems based on convolutional neural networks have shown excellent performance in human face inference. However, some malicious users may exploit such powerful systems to identify others' face images disclosed by victims' social network accounts, consequently obtaining private information. To address this emerging issue, synthesizing face protection images with visual and protective effects is essential. However, existing face protection methods encounter three critical problems: poor visual effect, limited protective effect, and trade‐off between visual and protective effects. To address these challenges, we propose a novel face protection approach in this article. Specifically, we design a generative adversarial network (GAN) framework with an autoencoder (AEGAN) as the generator to synthesize the protection images. It is worth noting that we introduce an interpolation upsampling module in the decoder in order to let the synthesized protection images evade recognition by powerful convolution‐based FR systems. Furthermore, we introduce an attention module with a perceptual loss in AEGAN to enhance the visual effects of synthesized images by AEGAN. Extensive experiments have shown that AEGAN not only can maintain the comfortable visual quality of synthesized images but also prevent the recognition of commercial FR systems, including Baidu and iKLYTEK.

show abstract

“…Domains in biometric de-identification include sensor-based biometrics, user psychological profile identification, aesthetic-based biometrics, and social behavior biometrics. 22 We should also not forget that the personal identification was done at the molecular level, namely the deoxyribonucleic acid (DNA) level. Many techniques are used to analyze human and non-human DNA samples.…”

Section: Editorialmentioning

confidence: 99%