Learning to Anonymize Faces for Privacy Preserving Action Detection

Abstract

There is an increasing concern in computer vision devices invading users' privacy by recording unwanted videos. On the one hand, we want the camera systems to recognize important events and assist human daily lives by understanding its videos, but on the other hand we want to ensure that they do not intrude people's privacy. In this paper, we propose a new principled approach for learning a video \emph{face anonymizer}. We use an adversarial training setting in which two competing systems fight: (1) a video anonymizer that modifies the original video to remove privacy-sensitive information while still trying to maximize spatial action detection performance, and (2) a discriminator that tries to extract privacy-sensitive information from the anonymized videos. The end result is a video anonymizer that performs pixel-level modifications to anonymize each person's face, with minimal effect on action detection performance. We experimentally confirm the benefits of our approach compared to conventional hand-crafted anonymization methods including masking, blurring, and noise adding. Code, demo, and more results can be found on our project page https://jason718.github.io/project/privacy/main.html.

arXiv commentECCV'18 camera ready

References in corpus (13)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Learning Face Representation from Scratch
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Large-Margin Softmax Loss for Convolutional Neural Networks
• SphereFace: Deep Hypersphere Embedding for Face Recognition
• Convolutional Two-Stream Network Fusion for Video Action Recognition
• Spatially Transformed Adversarial Examples
• Learning to track for spatio-temporal action localization
• Human Action Localization with Sparse Spatial Supervision
• Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning
• Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption