A Novel Approach for Privacy-Preserving Video Sharing

Get BibTex-formatted data

Author

Jianping Fan, Hangzai Luo, Mohand-Said Hacid, Elisa Bertino

Tech report number

CERIAS TR 2005-114

Entry type

proceedings

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

Date

2005

Key alpha

Video content privacy, statistical inferences, privacy-preserving video sharing, unlabeled samples.

Publisher

ACM

Publication Date

2005-01-01

Copyright

2005 ACM

Keywords

Video content privacy, statistical inferences, privacy-preserving video sharing, unlabeled samples.

BibTex-formatted data

To refer to this entry, you may select and copy the text below and paste it into your BibTex document. Note that the text may not contain all macros that BibTex supports.

@Proceedings{ Video content privacy, statistical inferences, privacy-preserving video sharing, unlabeled samples.,
	title = "A Novel Approach for Privacy-Preserving Video Sharing",
	author = "Jianping Fan, Hangzai Luo, Mohand-Said Hacid, Elisa Bertino ",
	year = "2005",
	publisher = "ACM",
	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",
	copyright = "2005 ACM",
	keywords = "Video content privacy, statistical inferences, privacy-preserving video sharing, unlabeled samples.",
}