Utility-Improved Key-Value Data Collection with Local Differential Privacy for Mobile Devices

doi:10.12142/ZTECOM.202204003

ZTE Communications ›› 2022, Vol. 20 ›› Issue (4): 15-21.DOI: 10.12142/ZTECOM.202204003

• Special Topic • Previous Articles Next Articles

Utility-Improved Key-Value Data Collection with Local Differential Privacy for Mobile Devices

TONG Ze, DENG Bowen, ZHENG Lele, ZHANG Tao()

School of Computer Science and Technology, Xidian University, Xi'an 710071, China

Received:2022-09-09 Online:2022-12-31 Published:2022-12-30
About author:TONG Ze received his BS degree from Chang’an University, China in 2019, where he is currently pursuing the MS degree with the School of Computer Science and Technology, Xidian University, China. His research interests include differential privacy and network security.|DENG Bowen received his BS degree from Xidian University, China in 2020, where he is currently pursuing the MS degree with the School of Computer Science and Technology, Xidian University. His research interests include differential privacy and social networks.|ZHENG Lele received his BS degree from Xidian University, China in 2018, where he is currently pursuing the PhD degree with the School of Computer Science and Technology, Xidian University. His research interests include differential privacy and the IoT data security.|ZHANG Tao (taozhang@xidian.edu.cn) received his MS and PhD degrees in computer science from Xidian University, China in 2011 and 2015, respectively. He is currently an associate professor with the School of Computer Science and Technology, Xidian University. His research interests include network security and privacy protection.

Abstract

Abstract:

The structure of key-value data is a typical data structure generated by mobile devices. The collection and analysis of the data from mobile devices are critical for service providers to improve service quality. Nevertheless, collecting raw data, which may contain various personal information, would lead to serious personal privacy leaks. Local differential privacy (LDP) has been proposed to protect privacy on the device side so that the server cannot obtain the raw data. However, existing mechanisms assume that all keys are equally sensitive, which cannot produce high-precision statistical results. A utility-improved data collection framework with LDP for key-value formed mobile data is proposed to solve this issue. More specifically, we divide the key-value data into sensitive and non-sensitive parts and only provide an LDP-equivalent privacy guarantee for sensitive keys and all values. We instantiate our framework by using a utility-improved key value-unary encoding (UKV-UE) mechanism based on unary encoding, with which our framework can work effectively for a large key domain. We then validate our mechanism which provides better utility and is suitable for mobile devices by evaluating it in two real datasets. Finally, some possible future research directions are envisioned.

Key words: key-value data, local differential privacy, mobile devices, privacy-preserving data collection

TONG Ze, DENG Bowen, ZHENG Lele, ZHANG Tao. Utility-Improved Key-Value Data Collection with Local Differential Privacy for Mobile Devices[J]. ZTE Communications, 2022, 20(4): 15-21.

Figures/Tables 4

References 23

1	ZENG J A, PLALE B. KVLight: A lightweight key-value store for distributed access in cloud [C]//The 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid). IEEE, 2016: 473–482. DOI: 10.1109/CCGrid.2016.55 DOI
2	SUN L, ZHAO J, YE X, et al. Conditional analysis for key-value data with local differential privacy [EB/OL]. (2019-07-11) [2022-09-20].
3	ANGELINI L, CAON M, CARRINO S, et al. Designing a desirable smart bracelet for older adults [C]//Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication. ACM, 2013: 425–434. DOI: 10.1145/2494091.2495974 DOI
4	MENG J K, ZHENG Z B, TAO G H, et al. User-specific rating prediction for mobile applications via weight-based matrix factorization [C]//Proceedings of 2016 IEEE International Conference on Web Services. IEEE, 2016: 728–731. DOI: 10.1109/ICWS.2016.104 DOI
5	BALAKRISHNAN S, CHOPRA S, APPLEGATE D, et al. Computational television advertising [C]//Proceedings of 2012 IEEE 12th International Conference on Data Mining. IEEE, 2012: 71–80. DOI: 10.1109/ICDM.2012.129 DOI
6	DUCHI J C, JORDAN M I, WAINWRIGHT M J. Local privacy and statistical minimax rates [C]//Proceedings of 2013 IEEE 54th Annual Symposium on Foundations of Computer Science. IEEE, 2013: 429–438. DOI: 10.1109/FOCS.2013.53 DOI
7	TANG J, KOROLOVA A, BAI X, et al. Privacy loss in apple’s implementation of differential privacy on macOS 10.12. [EB/OL]. [2022-09-20]. ’s_Implementation_of_Differential_Privacy_on_MacOS_1012
8	DING B, KULKARNI J, YEKHANIN S. Collecting telemetry data privately [C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, IEEE, 2017: 3574–3583
9	YE Q Q, HU H B, MENG X F, et al. PrivKV: key-value data collection with local differential privacy [C]//Proceedings of 2019 IEEE Symposium on Security and Privacy (SP). IEEE, 2019: 317–331. DOI: 10.1109/sp.2019.00018 DOI
10	GU X, LI M, CHENG Y, et al. PCKV: locally differentially private correlated key-value data collection with optimized utility [EB/OL]. (2019-11-28) [2022-09-20].
11	MURAKAMI T, KAWAMOTO Y. Utility-optimized local differential privacy mechanisms for distribution estimation [C]//Proceedings of the 28th USENIX Conference on Security Symposium. SEC, 2019: 1877–1894
12	DWORK C, MCSHERRY F, NISSIM K, et al. Calibrating noise to sensitivity in private data analysis [J]. Theory of cryptography, 2006: 265–284. DOI: 10.1007/11681878_14 DOI
13	ERLINGSSON Ú, PIHUR V, KOROLOVA A. RAPPOR: randomized aggregatable privacy-preserving ordinal response [C]//The 2014 ACM SIGSAC Conference on Computer and Communications Security. CCS, 2014: 1054–1067. DOI: 10.1145/2660267.2660348 DOI
14	WANG T H, LI N H, JHA S. Locally differentially private heavy hitter identification [J]. IEEE transactions on dependable and secure computing, 2021, 18(2): 982–993. DOI: 10.1109/TDSC.2019.2927695 DOI
15	WANG T H, BLOCKI J, LI N H, et al. Locally differentially private protocols for frequency estimation [C]//The 26th USENIX Conference on Security Symposium. USENIX, 2017: 729–745
16	SONG S, WANG Y Z, CHAUDHURI K. Pufferfish privacy mechanisms for correlated data [C]//Proceedings of the 2017 ACM International Conference on Management of Data. ACM, 2017: 1291–1306. DOI: 10.1145/3035918.3064025 DOI
17	NARAYANAN A, SHMATIKOV V. Myths and fallacies of “personally identifiable information” [J]. Communications of the ACM, 2010, 53(6): 24–26. DOI: 10.1145/1743546.1743558 DOI
18	WANG T H, LI N H, JHA S. Locally differentially private frequent itemset mining [C]//Proceedings of 2018 IEEE Symposium on Security and Privacy. IEEE, 2018: 127–143. DOI: 10.1109/SP.2018.00035 DOI
19	DUCHI J C, JORDAN M I, WAINWRIGHT M J. Minimax optimal procedures for locally private estimation [J]. Journal of the American statistical association, 2018, 113(521): 182–201. DOI: 10.1080/01621459.2017.1389735 DOI
20	WANG N, XIAO X K, YANG Y, et al. Collecting and analyzing multidimensional data with local differential privacy [C]//Proceedings of 2019 IEEE 35th International Conference on Data Engineering. IEEE, 2019: 638–649. DOI: 10.1109/ICDE.2019.00063 DOI
21	KAGGLE. Ecommerce rating dataset [EB/OL]. [2022-09-20].
22	KAGGLE. Clothing fit and rating dataset [EB/OL]. [2022-09-20].
23	WU Y J, CAO X Y, JIA J Y, et al. Poisoning attacks to local differential privacy protocols for key-value data [EB/OL]. (2021-11-22) [2022-09-20].

Utility-Improved Key-Value Data Collection with Local Differential Privacy for Mobile Devices

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 4

References 23

Related Articles 1

Recommended Articles

Metrics