VideoDP: A Flexible Platform for Video Analytics with Differential Privacy

Author:

Wang Han1,Xie Shangyu1,Hong Yuan1

Affiliation:

1. Illinois Institute of Technology

Abstract

Abstract Massive amounts of videos are ubiquitously generated in personal devices and dedicated video recording facilities. Analyzing such data would be extremely beneficial in real world (e.g., urban traffic analysis). However, videos contain considerable sensitive information, such as human faces, identities and activities. Most of the existing video sanitization techniques simply obfuscate the video by detecting and blurring the region of interests (e.g., faces, vehicle plates, locations and timestamps). Unfortunately, privacy leakage in the blurred video cannot be effectively bounded, especially against unknown background knowledge. In this paper, to our best knowledge, we propose the first differentially private video analytics platform (VideoDP) which flexibly supports different video analyses with rigorous privacy guarantee. Given the input video, VideoDP randomly generates a utility-driven private video in which adding or removing any sensitive visual element (e.g., human, and object) does not significantly affect the output video. Then, different video analyses requested by untrusted video analysts can be flexibly performed over the sanitized video with differential privacy. Finally, we conduct experiments on real videos, and the experimental results demonstrate that VideoDP can generate accurate results for video analytics.

Publisher

Walter de Gruyter GmbH

Subject

General Medicine

Reference59 articles.

1. [1] YouTube Official Blog 2012. (02/2020)

2. [2] https://boxy-dataset.com/boxy/ (02/2020)

3. [3] https://drive.google.com/file/d/1hYa5s7fjvQc1S1wRY6GcRqOPwL0Hy_aE/view. (02/2020)

4. [4] https://opencv.org/. (02/2020)

5. [5] 2012. H.R. 6671 (112th): Video Privacy Protection Act.

Cited by 16 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Trajectory-aware privacy-preserving method with local differential privacy in crowdsourcing;EURASIP Journal on Information Security;2024-09-02

2. Towards Accurate and Stronger Local Differential Privacy for Federated Learning with Staircase Randomized Response;Proceedings of the Fourteenth ACM Conference on Data and Application Security and Privacy;2024-06-19

3. Toward a Privacy-Preserving Face Recognition System: A Survey of Leakages and Solutions;ACM Computing Surveys;2024-06-17

4. DPI: Ensuring Strict Differential Privacy for Infinite Data Streaming;2024 IEEE Symposium on Security and Privacy (SP);2024-05-19

5. Differentially Private Video Activity Recognition;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3