Privid: Practical, Privacy-Preserving Video Analytics Queries


Publication/Creation Date
June 22 2021
Media Type
Journal Article
Persuasive Intent
Academic
Discursive Type
Inventions
Description
Abstract:

Analytics on video recorded by cameras in public areas have the potential to fuel many exciting applications, but also pose the risk of intruding on individuals' privacy. Unfortunately, existing solutions fail to practically resolve this tension between utility and privacy, relying on perfect detection of all private information in each video frame--an elusive requirement. This paper presents: (1) a new notion of differential privacy (DP) for video analytics, (ρ,K,ϵ)-event-duration privacy, which protects all private information visible for less than a particular duration, rather than relying on perfect detections of that information, and (2) a practical system called Privid that enforces duration-based privacy even with the (untrusted) analyst-provided deep neural networks that are commonplace for video analytics today. Across a variety of videos and queries, we show that Privid achieves accuracies within 79-99% of a non-private system.
HCI Platform
Ambient
Relation to Body
Around
Related Body Part
Entire Body
Augments
Protecting
Marketing Keywords
Privid
Source
https://doi.org/10.48550/arXiv.2106.12083

Date archived
May 5 2022
Last edited
May 5 2022
How to cite this entry
Frank Cangialosi, Neil Agarwal, Venkat Arun, Junchen Jiang, Srinivas Narayana, Anand Sarwate, Ravi Netravali. (June 22 2021). "Privid: Practical, Privacy-Preserving Video Analytics Queries". Fabric of Digital Life. https://fabricofdigitallife.com/Detail/objects/5734