Privacy at Scale: Local Differential Privacy in Practice

By Graham Cormode, Somesh Jha, Tejas D. Kulkarni, Ninghui Li, Divesh Srivastava, Tianhao Wang. 2018

307 citations recorded by the source corpus.

Local differential privacy (LDP), where users randomly perturb their inputs to provide plausible deniability of their data without the need for a trusted party, has been adopted recently by several major technology organizations, including Google, Apple and Microsoft. This tutorial aims to introduce the key technical underpinnings of these deployed systems, to survey current research that addresses related problems within the LDP model, and to identify relevant open problems and research directions for the community.

Subfields: Artificial Intelligence, Computer Science Applications, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Fangzhao Wu
2. Chuhan Wu
3. Yongfeng Huang
4. Xing Xie
5. Tao Qi
6. Fei Sun
7. Bin Cui
8. Shiwen Wu

In Computer Science Applications

1. Jun Zhao
2. Xing Xie
3. Siu Cheung Hui
4. Ge Yu
5. Jiankun Hu
6. Hyejin Shin
7. Ying Zhao
8. Ning Wang

In Sociology and Political Science

1. Jun Zhao
2. Xing Xie
3. Yuan Qi
4. Xiaolin Zheng
5. Chaochao Chen
6. Jiankun Hu
7. W. Fang
8. Ying Zhao

Citations in the corpus

• Collecting and Analyzing Multidimensional Data with Local Differential Privacy (2019, background): “This provides plausible deniability to the user [9].”
• Graph Neural Networks in Recommender Systems: A Survey (2020, background): “To reduce the amount of noise while maintaining privacy protection, PPGRec [120] converts the LDP model into the central differential privacy model and only adds noise to the aggregated global gradient.”
• A Survey on Differential Privacy for Unstructured Data Content (2022, methodology): “[16] reviewed local DP technologies deployed in Google, Apple, and Microsoft and identified several research issues in progress and in planning at that time.”
• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, methodology): “A local differential privacy technique is introduced to remove the trusted central authority demanded in global differential privacy [34, 102].”
• FedRec: Privacy-Preserving News Recommendation with Federated Learning (2020, background): “A classical scenario of LDP is that there are a set of users, and each user u has a private value v , which is sent to a untrusted third-party aggregator so that the aggregator can learn some statistical information of the private value distribution among the users (Cormode et al., 2018).”
• Practical Privacy Preserving POI Recommendation (2020, background): “Differential Privacy (DP) has been proposed in the global privacy context to ensure that an adversary should not be able to reliably infer whether or not a particular individual is participating in the database query, while Local Differential Privacy (LDP) was proposed in the local privacy context, ”