Who clicks there!: Anonymizing the photographer in a camera saturated society

TL;DR

This paper addresses privacy risks for photographers in social media, analyzing camera location detection attacks and proposing view synthesis as a potential privacy-preserving technique.

Contribution

It introduces the concept of camera location detection attacks and reviews existing defenses, suggesting view synthesis algorithms as a promising privacy solution.

Findings

Current obfuscation techniques do not protect camera location info

Anonymous publication methods are ineffective against camera location detection

View synthesis algorithms could offer probabilistic privacy guarantees

Abstract

In recent years, social media has played an increasingly important role in reporting world events. The publication of crowd-sourced photographs and videos in near real-time is one of the reasons behind the high impact. However, the use of a camera can draw the photographer into a situation of conflict. Examples include the use of cameras by regulators collecting evidence of Mafia operations; citizens collecting evidence of corruption at a public service outlet; and political dissidents protesting at public rallies. In all these cases, the published images contain fairly unambiguous clues about the location of the photographer (scene viewpoint information). In the presence of adversary operated cameras, it can be easy to identify the photographer by also combining leaked information from the photographs themselves. We call this the camera location detection attack. We propose and review defense techniques against such attacks. Defenses such as image obfuscation techniques do not protect camera-location information; current anonymous publication technologies do not help either. However, the use of view synthesis algorithms could be a promising step in the direction of providing probabilistic privacy guarantees.