1 |
A Framework for Measuring Privacy Risks of YouTubeCalero, Vanessa January 2020 (has links)
While privacy risks associated with known social networks such as Facebook and Instagram
are well studied, there is a limited investigation of privacy risks of YouTube
videos, which are mainly uploaded by teenagers and young adults, called YouTubers.
This research aims on quantifying the privacy risks of videos when sensitive
information about the private life of a YouTuber is being shared publicly. We developed
a privacy metric for YouTube videos called Privacy Exposure Index (PEI) extending
the existing social networking privacy frameworks. To understand the factors
moderating privacy behaviour of YouTubers, we conducted an extensive survey
of about 100 YouTubers. We have also investigated how YouTube Subscribers and
Viewers may desire to influence the privacy exposure of YouTubers through interactive
commenting on Videos or using other parallels YouTubers’ social networking
channels. For this purpose, we conducted a second survey of about 2000 viewers.
The results of these surveys demonstrate that YouTubers are concerned about their
privacy. Nevertheless inconsistent to this concern they exhibit privacy exposing behaviour
on their videos. In addition, we found YouTubers are being encouraged by
their audience to continue disclosing more personal information on new contents.
Finally, we empirically evaluated the soundness, consistency and applicability of
PEI by analyzing 100 videos uploaded by 10 YouTubers over a period of two years. / Thesis / Master of Science (MSc) / This research aims on quantifying the privacy risks of videos when sensitive
information about the private life of a YouTuber is being shared publicly.
|
2 |
Scene Understanding For Real Time Processing Of Queries Over Big Data Streaming VideoAved, Alexander 01 January 2013 (has links)
With heightened security concerns across the globe and the increasing need to monitor, preserve and protect infrastructure and public spaces to ensure proper operation, quality assurance and safety, numerous video cameras have been deployed. Accordingly, they also need to be monitored effectively and efficiently. However, relying on human operators to constantly monitor all the video streams is not scalable or cost effective. Humans can become subjective, fatigued, even exhibit bias and it is difficult to maintain high levels of vigilance when capturing, searching and recognizing events that occur infrequently or in isolation. These limitations are addressed in the Live Video Database Management System (LVDBMS), a framework for managing and processing live motion imagery data. It enables rapid development of video surveillance software much like traditional database applications are developed today. Such developed video stream processing applications and ad hoc queries are able to "reuse" advanced image processing techniques that have been developed. This results in lower software development and maintenance costs. Furthermore, the LVDBMS can be intensively tested to ensure consistent quality across all associated video database applications. Its intrinsic privacy framework facilitates a formalized approach to the specification and enforcement of verifiable privacy policies. This is an important step towards enabling a general privacy certification for video surveillance systems by leveraging a standardized privacy specification language. With the potential to impact many important fields ranging from security and assembly line monitoring to wildlife studies and the environment, the broader impact of this work is clear. The privacy framework protects the general public from abusive use of surveillance technology; iii success in addressing the "trust" issue will enable many new surveillance-related applications. Although this research focuses on video surveillance, the proposed framework has the potential to support many video-based analytical applications.
|
Page generated in 0.0435 seconds