Distribution Discrepancy Maximization for Image Privacy Preserving
arXiv:1811.07335
Abstract
With the rapid increase in online photo sharing activities, image obfuscation algorithms become particularly important for protecting the sensitive information in the shared photos. However, existing image obfuscation methods based on hand-crafted principles are challenged by the dramatic development of deep learning techniques. To address this problem, we propose to maximize the distribution discrepancy between the original image domain and the encrypted image domain. Accordingly, we introduce a collaborative training scheme: a discriminator is trained to discriminate the reconstructed image from the encrypted image, and an encryption model is required to generate these two kinds of images to maximize the recognition rate of , leading to the same training objective for both and . We theoretically prove that such a training scheme maximizes two distributions' discrepancy. Compared with commonly-used image obfuscation methods, our model can produce satisfactory defense against the attack of deep recognition models indicated by significant accuracy decreases on FaceScrub, Casia-WebFace and LFW datasets.
arXiv comment8 pages, 6 figures
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Learning Face Representation from Scratch
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
- Secure Direct Communication with a Quantum One-Time-Pad
- Fast Feature Fool: A data independent approach to universal adversarial perturbations
- Defeating Image Obfuscation with Deep Learning
- P3: Toward Privacy-Preserving Photo Sharing
- Faceless Person Recognition; Privacy Implications in Social Media
- Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective