A survey on security and privacy of federated learning

By Viraaji Mothukuri, R. Parizi, Seyedamin Pouriyeh, Yan-ping Huang, Ali Dehghantanha, Gautam Srivastava. Future generations computer systems, 2021

1,391 citations recorded by the source corpus.

Abstract Federated learning (FL) is a new breed of Artificial Intelligence (AI) that builds upon decentralized data and training that brings learning to the edge or directly on-device. FL is a new research area often referred to as a new dawn in AI, is in its infancy, and has not yet gained much trust in the community, mainly because of its (unknown) security and privacy implications. To advance the state of the research in this area and to realize extensive utilization of the FL approach and its mass adoption, its security and privacy concerns must be first identified, evaluated, and documented. FL is preferred in use-cases where security and privacy are the key concerns and having a clear view and understanding of risk factors enable an implementer/adopter of FL to successfully build a secure environment and gives researchers a clear vision on possible research areas. This paper aims to provide a comprehensive study concerning FL’s security and privacy aspects that can help bridge the gap between the current state of federated AI and a future in which mass adoption is possible. We present an illustrative description of approaches and various implementation styles with an examination of the current challenges in FL and establish a detailed review of security and privacy concerns that need to be considered in a thorough and clear context. Findings from our study suggest that overall there are fewer privacy-specific threats associated with FL compared to security threats. The most specific security threats currently are communication bottlenecks, poisoning, and backdoor attacks while inference-based attacks are the most critical to the privacy of FL. We conclude the paper with much needed future research directions to make FL adaptable in realistic scenarios.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/478df2ddc7159853d0da9c9d6fc2211077edbe80

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

Citations in the corpus

Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges (2022, background): “These surveys lack of an holistic view of FL and the review of the defences against adversarial attacks, because of the following reasons: (1) most of them are only focused on one kind of adversarial attacks, namely there are surveys reviewing attacks to the federated model [18, 19, 20] or privacy a”
Federated Learning in Edge Computing: A Systematic Survey (2022, background): “The original intent of FL was to resolve the issues related to data privacy, ownership, and legalization [80].”
Personalized Federated Learning using Hypernetworks (2021, background): “Federated learning (FL) (McMahan et al., 2017a; Kairouz et al., 2019; Mothukuri et al., 2021; Li et al., 2019; 2020a) is a learning setup in machine learning in which multiple clients collaborate to solve a learning task while maintaining privacy and communication efﬁciency.”
Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges (2022, background): “GBDTs have been especially popular recently due to their superior performance in many classiﬁcation and regression tasks [26].”
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2021, background): “Federated learning is a trending approach to resolve privacy issue in learning problems [45, 167, 192, 259].”
Decentralized Federated Learning: A Survey and Perspective (2023, background): “Although FL has shown unprecedented advantages, most of the current research has been limited to CFL. DFL, as an essential branch in FL, is proliferating and offering beneﬁts over CFL. Recent surveys have focused more on CFL, with less attention given to DFL [61], [75], [76], [77].”
Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challenges (2021, background): “In particular, a shared global model is learned using distributed local datasets under the control of a blockchain which also provides model veriﬁcation in a decentralized manner.”
From distributed machine learning to federated learning: a survey (2021, methodology): “Some surveys [89,114,129] focus on the data privacy and security of FL.”
A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022, background): “Instead of sending sensitive data to a server, data can remain on-device and only local model updates need to be sent off-device [39].”
Privacy and Robustness in Federated Learning: Attacks and Defenses (2020, background): “Section III presents a comprehensive review of the privacy attacks in FL, particularly targeting the sensitive information (class representative, membership, properties, training inputs and labels) in HFL with homogeneous architectures.”
Federated Learning: Opportunities and Challenges (2021, background): “Researchers have introduced various FL architectures, incentive mechanisms to foster user participation, cloud services for FL etc. Motivated by this growing [2, 14, 26, 36] are focused either on different federated learning architecture or on different challenges in FL domain.”