Faceless Person Recognition; Privacy Implications in Social Media

TL;DR

This paper investigates the privacy risks of social media data by analyzing person recognizability under various conditions, demonstrating that even minimal images can compromise user privacy despite obfuscation.

Contribution

It introduces a systematic framework for studying person recognition in social media and proposes a robust recognition system capable of handling diverse variations with limited training data.

Findings

Few images suffice to threaten user privacy.

Obfuscation does not fully prevent recognition.

Recognition accuracy remains high across variations.

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.