Privacy Protectability: An Information-theoretical Approach
Not on the map. Why?
Abstract (arXiv)
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, textitprivacy 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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 49 references that are in the map. First posted on arXiv 25 May 2023.
Builds on
25 of 49 references.
References · 25
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2016Deep Learning with Differential Privacycited by 2,682
- 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
- 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
- 2016Distribution-Free Predictive Inference For Regressioncited by 657
- 2015WIDER FACE: A Face Detection Benchmarkcited by 297
- 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
- 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
- 2015Inverting Visual Representations with Convolutional Networkscited by 168
13 more
- 2018Privacy Preserving Machine Learning: Threats and Solutionscited by 78
- 2020Privacy in Deep Learning: A Surveycited by 70
- 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
- 2018AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learningcited by 58
- 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
- 2021Survey: Leakage and Privacy at Inference Timecited by 44
- 2022Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Modelscited by 42
- 2019WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wildcited by 39
- 2020Privacy-preserving Collaborative Learning with Automatic Transformation Searchcited by 31
- 2020DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networkscited by 23
- 2021DP-Image: Differential Privacy for Image Data in Feature Spacecited by 23
- 2019Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environmentscited by 17
- 2021Privacy-Preserving Feature Selection with Secure Multiparty Computationcited by 12
Built on by
Citing papers per year: 2025: 1.
1 paper.