Project: Privacy protection in photos for social networks
Description
Social computing applications, such as online
social networks, have experienced a significant momentum in the last
decades. These applications enable users to collaboratively create,
manage and share resources with other users in real time. Although
they provide several benefits for users and organizations, these
applications also open new
privacy issues. Users typically specify privacy
preferences determining the accessibility and visibility of their data. However,
they might not be aware of exactly who can access the data, as
access can also be granted by other co-controllers of the data.
To
address this issue, recent work has proposed an approach in which the
privacy preferences of each user are enforced by blurring the portions of a
shared image that they do not want to disclose to other users [1].
This approach, however, only supports the blurring of faces, and other
portions of a image might disclose sensitive information (e.g., the location
where the image was taken). This project aims to extend the work in [1]
to provide a more fine-grained control on the portion of an image that
can be disclosed.
In particular, the project requires investigating
and adapting techniques for object recognition and manipulate
images based on the privacy preferences provided by subjects.
[1] P. Ilia, I. Polakis, E. Athanasopoulos, F.
Maggi, and S. Ioannidis.
Face/Off: Preventing Privacy Leakage From Photos in
Social Networks. In
Conference on Computer and Communications Security,
pages 781–792. ACM,
2015.
Details
- Student
-
Georgi Kostov
- Supervisor
-
Andrei Jalba
- Secondary supervisor
-
NZNicola Zannone