Authors
- Lingjuan Lyu
- Han Yu*
- Xingjun Ma*
- Chen Chen
- Lichao Sun*
- Jun Zhao*
- Qiang Yang*
- Philip S. Yu*
* External authors
Venue
- TNNLS 2022
Date
- 2022
Privacy and Robustness in Federated Learning: Attacks and Defenses
Han Yu*
Xingjun Ma*
Chen Chen
Lichao Sun*
Jun Zhao*
Qiang Yang*
Philip S. Yu*
* External authors
TNNLS 2022
2022
Abstract
As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models are facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol designs have been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct a comprehensive survey on privacy and robustness in federated learning over the past 5 years. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) privacy attacks and defenses; 3) poisoning attacks and defenses, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy- preserving FL, and their interplays with multidisciplinary goals of FL.
Related Publications
Existing collaborative self-supervised learning (SSL) schemes are not suitable for cross-client applications because of their expensive computation and large local data requirements. To address these issues, we propose MocoSFL, a collaborative SSL framework based on Split Fe…
Knowledge Distillation (KD) is a typical method for training a lightweight student model with the help of a well-trained teacher model. However, most KD methods require access to either the teacher's training data or model parameter, which is unrealistic. To tackle this prob…
In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. There have been numerous domain adaptation (DA) methods in both online and offline modes to improve cross-domain adaptat…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.