Getting the face behind the squares: reconstructing pixelized video streams

  • Authors:

  • Ludovico Cavedon;Luca Foschini;Giovanni Vigna

  • Affiliations:

  • University of California, Santa Barbara;University of California, Santa Barbara;University of California, Santa Barbara

  • Venue:
  • WOOT'11 Proceedings of the 5th USENIX conference on Offensive technologies
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Pixelization is a technique to make parts of an image impossible to discern by the human eye by artificially decreasing the image resolution. Pixelization, as other forms of image censorship, is effective at hiding parts of an image that might be offensive to the viewer. However, pixelization is also often used also to achieve anonymity, for example to make the features of a person's face unrecognizable or the defining characteristics of cars and building unidentifiable. This use of pixelization is somewhat effective in the case of still images, even though it is open to dictionary attacks. However, when used in videos, pixelization might be vulnerable to full reconstruction attacks. In this paper, we describe an attack against the anonymization of videos through pixelization. We develop an approach that, given a pixelized video, reconstructs the image being pixelized so that the human eye can clearly identify the object being protected. We implemented our approach and tested it against both artificial and real-world videos. The results of our experiments show that, in many cases, video pixelization does not provide sufficient guarantees of anonymity.