Privacy Protectability: An Information-theoretical Approach
This work addresses privacy concerns in edge-cloud video analytics systems, offering a theoretical metric to evaluate protection schemes, though it is incremental as it builds on existing privacy protection methods.
The paper tackles the problem of quantifying privacy protection in edge-cloud video analytics by proposing a new information-theoretic metric called privacy protectability, which characterizes the degree to which a video stream can be protected for a given task, and validates it with experiments on real data.
Recently, inference privacy has attracted increasing attention. The inference privacy concern arises most notably in the widely deployed edge-cloud video analytics systems, where the cloud needs the videos captured from the edge. The video data can contain sensitive information and subject to attack when they are transmitted to the cloud for inference. Many privacy protection schemes have been proposed. Yet, the performance of a scheme needs to be determined by experiments or inferred by analyzing the specific case. In this paper, we propose a new metric, \textit{privacy protectability}, to characterize to what degree a video stream can be protected given a certain video analytics task. Such a metric has strong operational meaning. For example, low protectability means that it may be necessary to set up an overall secure environment. We can also evaluate a privacy protection scheme, e.g., assume it obfuscates the video data, what level of protection this scheme has achieved after obfuscation. Our definition of privacy protectability is rooted in information theory and we develop efficient algorithms to estimate the metric. We use experiments on real data to validate that our metric is consistent with empirical measurements on how well a video stream can be protected for a video analytics task.