Towards Fair and Privacy-Preserving Federated Deep Models

By Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar, Yitong Li, Xingjun Ma, Jiong Jin, Han Yu, Kee Siong Ng. 2019

244 citations recorded by the source corpus.

The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggregate local model updates. Server-based solutions are prone to the problem of a single-point-of-failure. In this respect, collaborative learning frameworks, such as federated learning (FL), are more robust. Existing federated learning frameworks overlook an important aspect of participation: fairness. All parties are given the same final model without regard to their contributions. To address these issues, we propose a decentralized Fair and Privacy-Preserving Deep Learning (FPPDL) framework to incorporate fairness into federated deep learning models. In particular, we design a local credibility mutual evaluation mechanism to guarantee fairness, and a three-layer onion-style encryption scheme to guarantee both accuracy and privacy. Different from existing FL paradigm, under FPPDL, each participant receives a different version of the FL model with performance commensurate with his contributions. Experiments on benchmark datasets demonstrate that FPPDL balances fairness, privacy and accuracy. It enables federated learning ecosystems to detect and isolate low-contribution parties, thereby promoting responsible participation.

Subfields: Artificial Intelligence, Information Systems, Federated & Distributed Learning, Privacy & Security, AI Ethics, Fairness & Society

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. Lichao Sun
2. Lingjuan Lyu
3. Philip S. Yu
4. Qiang Yang
5. Dacheng Tao
6. Bo Du
7. Han Yu
8. Mang Ye

In Information Systems

1. Lingjuan Lyu
2. Philip S. Yu
3. Li-zhen Cui
4. Chris J. M. Yoon
5. Jun Zhao
6. Dacheng Tao
7. Gauri Joshi
8. Bo Du

In Federated & Distributed Learning

1. Lingjuan Lyu
2. Bo Du
3. Mang Ye
4. Philip S. Yu
5. Han Yu
6. Qiang Yang
7. Lichao Sun
8. Chris J. M. Yoon

In Privacy & Security

1. Lingjuan Lyu
2. Bo Du
3. Mang Ye
4. Philip S. Yu
5. Lichao Sun
6. Chris J. M. Yoon
7. Clement Fung
8. Ivan Beschastnikh

In AI Ethics, Fairness & Society

1. Lingjuan Lyu
2. Gauri Joshi
3. Yae Jee Cho
4. Jianyu Wang

Citations in the corpus

• Federated Model Distillation with Noise-Free Differential Privacy (2020, methodology): “In order to protect training data privacy in FL, various privacy protection techniques have been proposed in the literature [Geyer et al., 2017; McMahan et al., 2018; Bonawitz et al., 2017; Wang et al., 2019b; Zhao et al., 2020; Sun et al., 2021; Lyu et al., 2020].”
• Local Differential Privacy-Based Federated Learning for Internet of Things (2020, unknown): “Recently, LDP has attracted much attention [13]–[20].”
• Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies (2020, background): “[36] Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar, Yitong Li, Xingjun Ma, Jiong Jin, Han Yu, and Kee Siong Ng.”
• Towards Personalized Federated Learning (2021, background): “The study of fairness in FL is mostly focused on the prevailing server-based FL paradigm [103–105], although new work on fairness in alternative FL paradigms is emerging [106].”
• Biscotti: A Blockchain System for Private and Secure Federated Learning (2021, background): “2 To avoid directly sharing sensitive data, federated learning [5], [6], [7] is a prominent solution for large-scale secure multi-party ML: clients train a shared model through a trusted aggregator without revealing their underlying data or computation [8], [9], [10].”
• Federated Learning in Smart City Sensing: Challenges and Opportunities (2020, unknown): “Lyu et al. [154] consider fairness in their blockchain-enabled Federated Learning scheme.”
• Towards Understanding Biased Client Selection in Federated Learning (2022, background): “An interesting future direction is to improve the fairness (Li et al., 2020a; Yu et al., 2020; Lyu et al., 2020; Mohri et al., 2019) In Advances in Neural Information”
• Privacy and Robustness in Federated Learning: Attacks and Defenses (2020, background): “For example, [140], [141] addressed collab-”
• Heterogeneous Federated Learning: State-of-the-art and Research Challenges (2023, background): “Besides, the potential relationship between collaborative fairness and privacy protection [91, 145] needs to be further investigated.”
• Threats to Federated Learning: A Survey (2020, methodology): “Decentralized Federated Learning: Decentralized FL where no single server is required in the system is currently being studied [ Yang et al. , 2019b; Lyu et al. , 2019 ] .”