Poisoning Attack in Federated Learning using Generative Adversarial Nets

Zhang, Jiale; Chen, Junjun; Wu, Di; Chen, Bing; Yu, Shui

doi:10.1109/trustcom/bigdatase.2019.00057

Cited by 138 publications

(58 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the reputation metric, the central server selects the clients with high reputation values. Zhang et al [75] propose a poisoning attack against FL systems based on GAN.…”

Section: Privacy and Securitymentioning

confidence: 99%

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Yoshinaga

et al. 2020

IEEE Open J. Comput. Soc.

268

106

View full text Add to dashboard Cite

show abstract

“…Based on the reputation metric, the central server selects the clients with high reputation values. Zhang et al [75] propose a poisoning attack against FL systems based on GAN.…”

Section: Privacy and Securitymentioning

confidence: 99%

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Yoshinaga

et al. 2020

IEEE Open J. Comput. Soc.

268

106

View full text Add to dashboard Cite

show abstract

“…However, they can be more compelling given that they have demonstrated their ability to generate artificial samples that are statistically representative of the training data [76]. For instance, authors in [78] demonstrate how GAN can be used to get training samples through inference and use these recovered samples to poison the training data. An adversary can act as a benign participant and stealthily trains a GAN to simulate prototypical samples of the other clients' training set, which does not belong to the attacker.…”

Section: ) Gan Reconstruction Attacksmentioning

confidence: 99%

Vulnerabilities in Federated Learning

2021

View full text Add to dashboard Cite

With more regulations tackling the protection of users' privacy-sensitive data in recent years, access to such data has become increasingly restricted. A new decentralized training paradigm, known as Federated Learning (FL), enables multiple clients located at different geographical locations to learn a machine learning model collaboratively without sharing their data. While FL has recently emerged as a promising solution to preserve users' privacy, this new paradigm's potential security implications may hinder its widespread adoption. The existing FL protocols exhibit new unique vulnerabilities that adversaries can exploit to compromise the trained model. FL is often preferred in learning environments where security and privacy are the key concerns. Therefore, it is crucial to raise awareness of the consequences resulting from the new threats to FL systems. To date, the security of traditional machine learning systems has been widely examined. However, many open challenges and complex questions are still surrounding FL security. In this paper, we bridge the gap in FL literature by providing a comprehensive survey of the unique security vulnerabilities exposed by the FL ecosystem. We highlight the vulnerabilities sources, key attacks on FL, defenses, as well as their unique challenges, and discuss promising future research directions towards more robust FL.INDEX TERMS Attacks, defenses, Federated Learning, security threats, vulnerabilities.

show abstract

“…The work conducted by Bhagoji et al (2019) shows that Byzantine‐resilient aggregation is weak to defense this attack. Further, J. Zhang et al (2019) attempted to use generative adversarial networks to generate training data for model poisoning attacks. Backdoor Attacks: As for backdoor attacks, the federated model can be backdoored by one or multiple malicious participants using model replacement (Bagdasaryan et al, 2020). It's possible for the backdoor to label certain tasks incorrectly while retaining the accuracy of the global model.…”

Section: Challenges In Federated Learningmentioning

confidence: 99%

A survey on federated learning in data mining

Mao

et al. 2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Data mining is a process to extract unknown, hidden, and potentially useful information from data. But the problem of data island makes it arduous for people to collect and analyze scattered data, and there is also a privacy security issue when mining data. A collaboratively decentralized approach called federated learning unites multiple participants to generate a shareable global optimal model and keeps privacy‐sensitive data on local devices, which may bring great hope to us for solving the problems of decentralized data and privacy protection. Though federated learning has been widely used, few systematic studies have been conducted on the subject of federated learning in data mining. Hence, different from prior reviews in this field, we make a comprehensive summary and provide a novel taxonomy of the application of federated learning in data mining. This article starts by providing a thorough description of the relevant definitions and concepts, followed by an in‐depth investigation on the challenges faced by federated learning. In this context, we elaborate four taxonomies of major applications of federated learning in data mining, including education, healthcare, IoT, and intelligent transportation, and discuss them comprehensively. Finally, we discuss four promising research directions for further research, that is, privacy enhancement, improvement of communication efficiency, heterogeneous system processing, and reducing economic costs. This article is categorized under: Technologies > Machine Learning Fundamental Concepts of Data and Knowledge > Big Data Mining Technologies > Artificial Intelligence

show abstract

Poisoning Attack in Federated Learning using Generative Adversarial Nets

Cited by 138 publications

References 12 publications

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Vulnerabilities in Federated Learning

A survey on federated learning in data mining

Contact Info

Product

Resources

About