Federated Learning With Differential Privacy: Algorithms and Performance Analysis

By Kang Wei, Jun Li, Ming Ding, Chuan Ma, Howard H. Yang, Farokhi Farhad, Shi Jin, Tony Q. S. Quek, H. Vincent Poor. IEEE Transactions on Information Forensics and Security, 2019

2,251 citations recorded by the source corpus.

Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients’ private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from clients, e.g., weights trained in deep neural networks. In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noise is added to parameters at the clients’ side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noise. Then we develop a theoretical convergence bound on the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three key properties: 1) there is a tradeoff between convergence performance and privacy protection levels, i.e., better convergence performance leads to a lower protection level; 2) given a fixed privacy protection level, increasing the number <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> of overall clients participating in FL can improve the convergence performance; and 3) there is an optimal number aggregation times (communication rounds) in terms of convergence performance for a given protection level. Furthermore, we propose a <inline-formula> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula>-client random scheduling strategy, where <inline-formula> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> (<inline-formula> <tex-math notation="LaTeX">$1\leq K< N$ </tex-math></inline-formula>) clients are randomly selected from the <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> overall clients to participate in each aggregation. We also develop a corresponding convergence bound for the loss function in this case and the <inline-formula> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula>-client random scheduling strategy also retains the above three properties. Moreover, we find that there is an optimal <inline-formula> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> that achieves the best convergence performance at a fixed privacy level. Evaluations demonstrate that our theoretical results are consistent with simulations, thereby facilitating the design of various privacy-preserving FL algorithms with different tradeoff requirements on convergence performance and privacy levels.

Subfields: Artificial Intelligence, Federated & Distributed Learning, Privacy & Security

View Paper: https://arxiv.org/abs/1911.00222

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. Philip S. Yu
  2. Qiang Yang
  3. Lichao Sun
  4. Ming Ding
  5. Amir Salman Avestimehr
  6. Bo Li
  7. Basak Guler
  8. Jinhyun So

In Federated & Distributed Learning

  1. Amir Salman Avestimehr
  2. Jinhyun So
  3. Basak Guler
  4. Qiang Yang
  5. Mingzhe Chen
  6. Philip S. Yu
  7. Jiankun Hu
  8. Yanming Zhu

In Privacy & Security

  1. Basak Guler
  2. Amir Salman Avestimehr
  3. Jinhyun So
  4. Philip S. Yu
  5. Nguyen Binh Truong
  6. Hangyu Zhu
  7. Bo Li
  8. Aruna Prasad Seneviratne

Citations in the corpus