Differentially Private Federated Learning: A Client Level Perspective

By Robin C. Geyer, Tassilo Johannes Klein, Moin Nabi. 2017

1,680 citations recorded by the source corpus.

Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to share the data. However, the protocol is vulnerable to differential attacks, which could originate from any party contributing during federated optimization. In such an attack, a client's contribution during training and information about their data set is revealed through analyzing the distributed model. We tackle this problem and propose an algorithm for client sided differential privacy preserving federated optimization. The aim is to hide clients' contributions during training, balancing the trade-off between privacy loss and model performance. Empirical studies suggest that given a sufficiently large number of participating clients, our proposed procedure can maintain client-level differential privacy at only a minor cost in model performance.

Subfields: Artificial Intelligence, Computer Science Applications, Federated & Distributed Learning, Privacy & Security

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. Qiang Yang
  2. Peter Richtárik
  3. Percy Liang
  4. Martin Jaggi
  5. Philip S. Yu
  6. Yang Liu
  7. Quoc V. Le
  8. Jakub Konecný

In Computer Science Applications

  1. Ling Liu
  2. Jakub Konecný
  3. Carole-Jean Wu
  4. Young Geun Kim
  5. Dusist Niyato
  6. H. Vincent Poor
  7. Yaochu Jin
  8. Hadi Esmaeilzadeh

In Federated & Distributed Learning

  1. Qiang Yang
  2. Virginia Smith
  3. Chaoyang He
  4. Peter Richtárik
  5. Jakub Konecný
  6. Murali Annavaram
  7. Tian Li
  8. Yang Liu

In Privacy & Security

  1. Qiang Yang
  2. Lingjuan Lyu
  3. Vitaly Shmatikov
  4. Amir Salman Avestimehr
  5. Ramesh Raskar
  6. Praneeth Vepakomma
  7. Congzheng Song
  8. Mario Fritz

Citations in the corpus