A Novel Approach for Privacy-Preserving Video Sharing
Author
Jianping Fan, Hangzai Luo, Mohand-Said Hacid, Elisa Bertino
Tech report number
CERIAS TR 2005-114
Abstract
To support privacy-preserving video sharing, we have pro-
posed a novel framework that is able to protect the video
content privacy at the individual video clip level and pre-
vent statistical inferences from video collections. To protect
the video content privacy at the individual video clip level,
we have developed an effective algorithm to automatically
detect privacy-sensitive video ob jects and video events. To
prevent the statistical inferences from video collections, we
have developed a distributed framework for privacy-preserving
classifier training, which is able to significantly reduce the
costs of data transmission and reliably limit the privacy
breaches by determining the optimal size of blurred test
samples for classifier validation. Our experiments on a spe-
cific domain of patient training and counseling videos show
convincing results
Key alpha
Video content privacy, statistical inferences, privacy-preserving video sharing, unlabeled samples.
Publication Date
2005-01-01
Keywords
Video content privacy, statistical inferences, privacy-preserving video sharing, unlabeled samples.