SensitiveNets: Learning Agnostic Representations with Application to Face Images.
@article{Morales2020SensitiveNetsLA, title={SensitiveNets: Learning Agnostic Representations with Application to Face Images.}, author={A. Morales and Julian Fierrez and Rub{\'e}n Vera-Rodriguez and R. Tolosana}, journal={IEEE transactions on pattern analysis and machine intelligence}, year={2020}, volume={PP} }
This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data protection forces data controllers to guarantee privacy and avoid discriminative hazards while managing sensitive data of users. In our approach, privacy and discrimination are related to each other. Instead of existing approaches aimed directly at fairness… CONTINUE READING
Topics from this paper
11 Citations
FlowSAN: Privacy-Enhancing Semi-Adversarial Networks to Confound Arbitrary Face-Based Gender Classifiers
- Computer Science
- IEEE Access
- 2019
- 15
- PDF
PrivacyNet: Semi-Adversarial Networks for Multi-Attribute Face Privacy
- Computer Science, Medicine
- IEEE Transactions on Image Processing
- 2020
- 7
- PDF
SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning
- Computer Science
- ArXiv
- 2020
- 4
- PDF
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection
- Computer Science
- Inf. Fusion
- 2020
- 66
- PDF
InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics
- Computer Science
- ArXiv
- 2020
- 7
- PDF
Investigating Bias and Fairness in Facial Expression Recognition
- Computer Science
- ECCV Workshops
- 2020
- 4
- PDF
One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
- Computer Science
- ArXiv
- 2021
- PDF
FairCVtest Demo: Understanding Bias in Multimodal Learning with a Testbed in Fair Automatic Recruitment
- Computer Science
- ICMI
- 2020
- PDF
References
SHOWING 1-10 OF 20 REFERENCES
Semi-adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images
- Computer Science
- 2018 International Conference on Biometrics (ICB)
- 2018
- 48
- Highly Influential
- PDF
Discovering Fair Representations in the Data Domain
- Computer Science
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2019
- 24
- Highly Influential
- PDF
Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning
- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
- 22
- PDF
Learning Adversarially Fair and Transferable Representations
- Computer Science, Mathematics
- ICML
- 2018
- 203
- Highly Influential
- PDF
Learning Not to Learn: Training Deep Neural Networks With Biased Data
- Computer Science
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2019
- 62
- Highly Influential
- PDF
Deep Learning Face Attributes in the Wild
- Computer Science
- 2015 IEEE International Conference on Computer Vision (ICCV)
- 2015
- 3,056
- PDF
Measuring the Gender and Ethnicity Bias in Deep Models for Face Recognition
- Computer Science
- CIARP
- 2018
- 10
- PDF
Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings
- Computer Science
- ECCV Workshops
- 2018
- 72
- Highly Influential
- PDF
FaceNet: A unified embedding for face recognition and clustering
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 5,918
- PDF
FaceQnet: Quality Assessment for Face Recognition based on Deep Learning
- Computer Science, Engineering
- 2019 International Conference on Biometrics (ICB)
- 2019
- 22
- PDF