On Safeguarding Privacy and Security in the Framework of Federated Learning

Ma, Chuan; Li, Jun; Ding, Ming; Yang, Howard H.; Feng, Suili; Quek, Tony Q. S.; Poor, H. Vincent

doi:10.1109/mnet.001.1900506

Cited by 227 publications

(108 citation statements)

References 17 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…So, if the trained model is released, what happens is unexpected information reveal to hackers. It is also possible to obtain data of a victim by instantiating requests to the model [122]. This occurs when someone gains unauthorized permission to make prediction requests on a model that has been trained.…”

Section: Challenges and Limitations Of Federated Learningmentioning

confidence: 99%

“…In terms of trust, this mainly deals with the possibility of information leakage and preventing that from occurring [128]. Trust is needed in the medical and healthcare industries so that confidence in FL and FL's performance can be established [122]. Regarding trust, there are two types of collaboration participating FL entities can be in:…”

Section: Challenges and Limitations Of Federated Learningmentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

et al. 2020

View full text Add to dashboard Cite

This paper provides a comprehensive study of Federated Learning (FL) with an emphasis on enabling software and hardware platforms, protocols, real-life applications and use-cases. FL can be applicable to multiple domains but applying it to different industries has its own set of obstacles. FL is known as collaborative learning, where algorithm(s) get trained across multiple devices or servers with decentralized data samples without having to exchange the actual data. This approach is radically different from other more established techniques such as getting the data samples uploaded to servers or having data in some form of distributed infrastructure. FL on the other hand generates more robust models without sharing data, leading to privacy-preserved solutions with higher security and access privileges to data. This paper starts by providing an overview of FL. Then, it gives an overview of technical details that pertain to FL enabling technologies, protocols, and applications. Compared to other survey papers in the field, our objective is to provide a more thorough summary of the most relevant protocols, platforms, and real-life use-cases of FL to enable data scientists to build better privacy-preserving solutions for industries in critical need of FL. We also provide an overview of key challenges presented in the recent literature and provide a summary of related research work. Moreover, we explore both the challenges and advantages of FL and present detailed service use-cases to illustrate how different architectures and protocols that use FL can fit together to deliver desired results.

show abstract

Section: Challenges and Limitations Of Federated Learningmentioning

confidence: 99%

Section: Challenges and Limitations Of Federated Learningmentioning

confidence: 99%

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The aggregator simply communicates (using wired or wireless communications standards such as WiFi, UMTS, LTE, ZigBee) with the individual devices to share ML model parameters, and iteratively converges on the optimal configuration. Though FL by default is a significantly privacy-enhancing technology, recent efforts have showcased the possibility of privacy breaches using such a technology [9], [10]. Consequently, a proposed solution has been to add a privacy layer atop FL [9].…”

Section: Background Previewmentioning

confidence: 99%

Corrections to “Preference-Based Privacy Markets”

et al. 2021

View full text Add to dashboard Cite

“…Usually, in the traditional FL settings, the aggregation weight depends on the size of training, where the intelligent aggregator should be designed for multiple purposes. In [ 44 ], the authors proposed an intelligent aggregation method in order to address the problem of malicious clients. The authors also add a test process on the server, where the aggregator runs the test performance based on the uploaded parameters from the individual client.…”

Section: Critical Evaluation Of Flmentioning

confidence: 99%

A Critical Evaluation of Privacy and Security Threats in Federated Learning

Asad

Moustafa

2020

Sensors

View full text Add to dashboard Cite

With the advent of smart devices, smartphones, and smart everything, the Internet of Things (IoT) has emerged with an incredible impact on the industries and human life. The IoT consists of millions of clients that exchange massive amounts of critical data, which results in high privacy risks when processed by a centralized cloud server. Motivated by this privacy concern, a new machine learning paradigm has emerged, namely Federated Learning (FL). Specifically, FL allows for each client to train a learning model locally and performs global model aggregation at the centralized cloud server in order to avoid the direct data leakage from clients. However, despite this efficient distributed training technique, an individual’s private information can still be compromised. To this end, in this paper, we investigate the privacy and security threats that can harm the whole execution process of FL. Additionally, we provide practical solutions to overcome those attacks and protect the individual’s privacy. We also present experimental results in order to highlight the discussed issues and possible solutions. We expect that this work will open exciting perspectives for future research in FL.

show abstract

On Safeguarding Privacy and Security in the Framework of Federated Learning

Cited by 227 publications

References 17 publications

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Corrections to “Preference-Based Privacy Markets”

A Critical Evaluation of Privacy and Security Threats in Federated Learning

Contact Info

Product

Resources

About