FlowSAN: Privacy-Enhancing Semi-Adversarial Networks to Confound Arbitrary Face-Based Gender Classifiers
By Vahid Mirjalili, Sebastian Raschka, Arun A. Ross. 2019
50 citations recorded by the source corpus.
Privacy concerns in the modern digital age have prompted researchers to develop techniques that allow users to selectively suppress certain information in collected data while allowing for other information to be extracted. In this regard, semi-adversarial networks (SANs) have recently emerged as a method for imparting soft-biometric privacy to face images. SAN enables modifications of input face images so that the resulting face images can still be reliably used by arbitrary conventional face matchers for recognition purposes, while attribute classifiers, such as gender classifiers, are confounded. However, the generalizability of SANs across arbitrary gender classifiers has remained an open concern. In this paper, we propose a new method, FlowSAN, for allowing SANs to generalize to multiple gender classifiers. We propose stacking a diverse set of SAN models to compensate each other’s weaknesses, thereby forming a robust model with improved generalization capability. Extensive experiments using different unseen gender classifiers and face matchers demonstrate the efficacy of the proposed paradigm in imparting gender privacy to face images.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Ramesh Raskar
- Otkrist Gupta
- Praneeth Vepakomma
- Fatemehsadat Mirshghallah
- Hadi Esmaeilzadeh
- Abhishek Singh
- Mohammadkazem Taram
- Luc Van Gool
In Signal Processing
- Hadi Esmaeilzadeh
- Ramesh Raskar
- Fatemehsadat Mirshghallah
- Abhishek Singh
- Mohammadkazem Taram
- Praneeth Vepakomma
Citations in the corpus
- NoPeek: Information leakage reduction to share activations in distributed deep learning (2020, background): “…loss based privacy: These can be categorized into hiding specific sensitive attributes using adversarial training that reaches an equilibrium based on information theoretic loss functions optimized under minimax settings through learning weights of deep learning models [29, 30, 31, 32, 33, 34, 35].”
- Privacy in Deep Learning: A Survey (2020, background): “There is a body of work studying information-theoretic based methods for both privacy and fairness, where privacy and fairness are provided through information degradation, through obfuscation or adversarial learning and demonstrated by mutual information reduction (Diaz et al., 2018; Pinceti et al.”