PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy

Abstract

Recent research has established the possibility of deducing soft-biometric attributes such as age, gender and race from an individual's face image with high accuracy. However, this raises privacy concerns, especially when face images collected for biometric recognition purposes are used for attribute analysis without the person's consent. To address this problem, we develop a technique for imparting soft biometric privacy to face images via an image perturbation methodology. The image perturbation is undertaken using a GAN-based Semi-Adversarial Network (SAN) - referred to as PrivacyNet - that modifies an input face image such that it can be used by a face matcher for matching purposes but cannot be reliably used by an attribute classifier. Further, PrivacyNet allows a person to choose specific attributes that have to be obfuscated in the input face images (e.g., age and race), while allowing for other types of attributes to be extracted (e.g., gender). Extensive experiments using multiple face matchers, multiple age/gender/race classifiers, and multiple face datasets demonstrate the generalizability of the proposed multi-attribute privacy enhancing method across multiple face and attribute classifiers.

13 pages, 9 figures

References in corpus (9)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Synthesizing Robust Adversarial Examples
• Deep Identity-aware Transfer of Facial Attributes
• Facial Soft Biometrics for Recognition in the Wild: Recent Works, Annotation, and COTS Evaluation
• Face Recognition: From Traditional to Deep Learning Methods
• Descriptors and regions of interest fusion for gender classification in the wild. Comparison and combination with Convolutional Neural Networks
• Right for the Right Reason: Training Agnostic Networks

Cited by in corpus (11)

• Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
• A Survey of Privacy Vulnerabilities of Mobile Device Sensors
• Privacy Intelligence: A Survey on Image Privacy in Online Social Networks
• On Generating Identifiable Virtual Faces
• Generative Adversarial Networks: A Survey Towards Private and Secure Applications
• High Resolution Face Editing with Masked GAN Latent Code Optimization
• Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation Approach
• DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue
• Quantifying the Extent to Which Race and Gender Features Determine Identity in Commercial Face Recognition Algorithms
• Adversarial Machine Learning-Enabled Anonymization of OpenWiFi Data
• Intelligent Frame Selection as a Privacy-Friendlier Alternative to Face Recognition