Faceless Person Recognition; Privacy Implications in Social Media
arXiv:1607.08438
Abstract
As we shift more of our lives into the virtual domain, the volume of data shared on the web keeps increasing and presents a threat to our privacy. This works contributes to the understanding of privacy implications of such data sharing by analysing how well people are recognisable in social media data. To facilitate a systematic study we define a number of scenarios considering factors such as how many heads of a person are tagged and if those heads are obfuscated or not. We propose a robust person recognition system that can handle large variations in pose and clothing, and can be trained with few training samples. Our results indicate that a handful of images is enough to threaten users' privacy, even in the presence of obfuscation. We show detailed experimental results, and discuss their implications.
arXiv commentAccepted to ECCV'16
References in corpus (1)
Cited by in corpus (13)
- Examining the Impact of Blur on Recognition by Convolutional Networks
- Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
- Defeating Image Obfuscation with Deep Learning
- Learning Deep Features via Congenerous Cosine Loss for Person Recognition
- Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective
- Image Obfuscation for Privacy-Preserving Machine Learning
- A Hybrid Model for Identity Obfuscation by Face Replacement
- Learning to Succeed while Teaching to Fail: Privacy in Closed Machine Learning Systems
- Natural and Effective Obfuscation by Head Inpainting
- Sequential Person Recognition in Photo Albums with a Recurrent Network
- Distribution Discrepancy Maximization for Image Privacy Preserving
- Zoom-RNN: A Novel Method for Person Recognition Using Recurrent Neural Networks
- Learning to Collaborate for User-Controlled Privacy