Affiliation:
1. Xidian University, School of Computer Science and Technology, Xi'an, China
2. Rice University, Department of Computer Science, Houston, TX, USA
3. Rice University, Department of Electrical & Computer Engineering, Houston, TX, USA
Abstract
The remarkable success of machine learning has fostered a growing number of cloud-based intelligent services for mobile users. Such a service requires a user to send data, e.g. image, voice and video, to the provider, which presents a serious challenge to user privacy. To address this, prior works either obfuscate the data, e.g. add noise and remove identity information, or send representations extracted from the data, e.g. anonymized features. They struggle to balance between the service utility and data privacy because obfuscated data reduces utility and extracted representation may still reveal sensitive information.
This work departs from prior works in methodology: we leverage adversarial learning to better balance between privacy and utility. We design a representation encoder that generates the feature representations to optimize against the privacy disclosure risk of sensitive information (a measure of privacy) by the privacy adversaries, and concurrently optimize with the task inference accuracy (a measure of utility) by the utility discriminator. The result is the privacy adversarial network (PAN), a novel deep model with the new training algorithm, that can automatically learn representations from the raw data. And the trained encoder can be deployed on the user side to generate representations that satisfy the task-defined utility requirements and the user-specified/agnostic privacy budgets.
Intuitively, PAN adversarially forces the extracted representations to only convey information required by the target task. Surprisingly, this constitutes an implicit regularization that actually improves task accuracy. As a result, PAN achieves better utility and better privacy at the same time! We report extensive experiments on six popular datasets, and demonstrate the superiority of PAN compared with alternative methods reported in prior work.
Funder
Shaanxi Fund
NSF
NSFC
National Key R$\&$D Program of China
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture,Human-Computer Interaction
Cited by
22 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. Context-Aware Hybrid Encoding for Privacy-Preserving Computation in IoT Devices;IEEE Internet of Things Journal;2024-01-01
2. VAX;Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies;2023-09-27
3. APter: Privacy Enhancement in Deep Learning Services following Principle of Least Privilege;Proceedings of the ACM Turing Award Celebration Conference - China 2023;2023-07-28
4. GAPter: Gray-Box Data Protector for Deep Learning Inference Services at User Side;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04
5. Enhanced Embedded AutoEncoders: An Attribute-Preserving Face De-Identification Framework;IEEE Internet of Things Journal;2023-06-01