Vulnerabilities in Federated Learning

Bouacida, Nader; Mohapatra, Prasant

doi:10.1109/access.2021.3075203

Cited by 113 publications

(48 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FL [7][8][9][10][11][12][13] is a ML-based framework in which numerous clients cooperate to solve a ML problem, under the supervision and the coordination of a central server usually referred to as FL server. In other words, "it is a distributed ML strategy that generates a global model by learning from multiple decentralized edge clients.…”

Section: Basics Of Federated Learningmentioning

confidence: 99%

“…However, as secure as the FL seems, it by itself does not give the levels of privacy and security demanded by today's distributed systems requirements [9]. Beyond fundamental and FL-specific restrictions, the security of FL systems themselves are essential for developing networks where users can collaborate, learn, and most importantly trust.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Security of Federated Learning: Attacks, Defensive Mechanisms, and Challenges

Benmalek¹,

Benrekia²,

Challal³

2022

RIA

View full text Add to dashboard Cite

Recently, a new Artificial Intelligence (AI) paradigm, known as Federated Learning (FL), has been introduced. It is a decentralized approach to apply Machine Learning (ML) on-device without risking the disclosure and tracing of sensitive and private information. Instead of training the global model on a centralized server (by aggregating the clients’ private data), FL trains a global shared model by only aggregating clients’ locally-computed updates (the clients’ private data remains distributed across the clients’ devices). However, as secure as the FL seems, it by itself does not give the levels of privacy and security required by today’s distributed systems. This paper seeks to provide a holistic view of FL’s security concerns. We outline the most important attacks and vulnerabilities that are highly relevant to FL systems. Then, we present the recent proposed defensive mechanisms. Finally, we highlight the outstanding challenges, and we discuss the possible future research directions.

show abstract

Section: Basics Of Federated Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Security of Federated Learning: Attacks, Defensive Mechanisms, and Challenges

Benmalek¹,

Benrekia²,

Challal³

2022

RIA

View full text Add to dashboard Cite

show abstract

“…Anomaly detection methods actively identify and stops malicious updates from affecting the system [44,9]. These methods may be also used in FL systems to identify potential threats [17]. One frequent technique for handling untargeted adversaries is to calculate a specific test error rate on updates and reject those disadvantageous or neutral to the global model [9].…”

Section: Anomaly Detectionmentioning

confidence: 99%

Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms

Hallaji,

Razavi-Far,

Saif

2022

Preprint

View full text Add to dashboard Cite

The advent of federated learning has facilitated large-scale data exchange amongst machine learning models while maintaining privacy. Despite its brief history, federated learning is rapidly evolving to make wider use more practical. One of the most significant advancements in this domain is the incorporation of transfer learning into federated learning, which overcomes fundamental constraints of primary federated learning, particularly in terms of security. This chapter performs a comprehensive survey on the intersection of federated and transfer learning from a security point of view. The main goal of this study is to uncover potential vulnerabilities and defense mechanisms that might compromise the privacy and performance of systems that use federated and transfer learning.

show abstract

“…(2) the vast majority does not include any experimental study [24,25,26,27,28], so it is not possible to compare the strength of the attacks and the robustness of the defences in a common evaluation framework; and (3) by default they only focus on horizontal FL ignoring vertical and federated transfer learning.…”

Section: Introductionmentioning

confidence: 99%

Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges

Rodríguez-Barroso¹,

López²,

Luzón³

et al. 2022

Preprint

View full text Add to dashboard Cite

Federated learning is a machine learning paradigm that emerges as a solution to the privacy-preservation demands in artificial intelligence. As machine learning, federated learning is threatened by adversarial attacks against the integrity of the learning model and the privacy of data via a distributed approach to tackle local and global learning. This weak point is exacerbated by the inaccessibility of data in federated learning, which makes harder the protection against adversarial attacks and evidences the need to furtherance the research on defence methods to make federated learning a real solution for safeguarding data privacy. In this paper, we present an extensive review of the threats of federated learning, as well as as their corresponding countermeasures, attacks versus defences. This survey provides a taxonomy of adversarial attacks and a taxonomy of defence methods that depict a general picture of this vulnerability of federated learning and how to overcome it. Likewise, we expound guidelines for selecting the most adequate defence method according to the category of the adversarial attack. Besides, we carry out an extensive experimental study from which we draw further conclusions about the behaviour of attacks and defences and the guidelines for selecting the most adequate defence method according to the category of the adversarial attack. This study is finished leading to meditated learned lessons and challenges.

show abstract

Vulnerabilities in Federated Learning

Cited by 113 publications

References 66 publications

Security of Federated Learning: Attacks, Defensive Mechanisms, and Challenges

Security of Federated Learning: Attacks, Defensive Mechanisms, and Challenges

Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms

Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges

Contact Info

Product

Resources

About