English
Related papers

Related papers: ByzSecAgg: A Byzantine-Resistant Secure Aggregatio…

200 papers

In this paper, we propose a robust aggregation method for federated learning (FL) that can effectively tackle malicious Byzantine attacks. At each user, model parameter is firstly updated by multiple steps, which is adjustable over…

Machine Learning · Computer Science 2023-08-22 Shiyuan Zuo , Rongfei Fan , Han Hu , Ning Zhang , Shimin Gong

Byzantine attacks during model aggregation in Federated Learning (FL) threaten training integrity by manipulating malicious clients' updates. Existing methods struggle with limited robustness under high malicious client ratios and…

Cryptography and Security · Computer Science 2025-05-20 Yanhua Wen , Lu Ai , Gang Liu , Chuang Li , Jianhao Wei

Federated learning (FL) has recently gained significant momentum due to its potential to leverage large-scale distributed user data while preserving user privacy. However, the typical paradigm of FL faces challenges of both privacy and…

Cryptography and Security · Computer Science 2025-05-29 Sizai Hou , Songze Li , Tayyebeh Jahani-Nezhad , Giuseppe Caire

Decentralized learning involves training machine learning models over remote mobile devices, edge servers, or cloud servers while keeping data localized. Even though many studies have shown the feasibility of preserving privacy, enhancing…

Cryptography and Security · Computer Science 2022-01-07 Minghui Xu , Zongrui Zou , Ye Cheng , Qin Hu , Dongxiao Yu , Xiuzhen Cheng

While being an effective framework of learning a shared model across multiple edge devices, federated learning (FL) is generally vulnerable to Byzantine attacks from adversarial edge devices. While existing works on FL mitigate such…

Machine Learning · Computer Science 2022-11-01 Youngjoon Lee , Sangwoo Park , Joonhyuk Kang

As a promising distributed learning technology, analog aggregation based federated learning over the air (FLOA) provides high communication efficiency and privacy provisioning under the edge computing paradigm. When all edge devices…

Machine Learning · Computer Science 2022-04-15 Xin Fan , Yue Wang , Yan Huo , Zhi Tian

Random linear network coding can be used in peer-to-peer networks to increase the efficiency of content distribution and distributed storage. However, these systems are particularly susceptible to Byzantine attacks. We quantify the impact…

Networking and Internet Architecture · Computer Science 2016-11-17 MinJi Kim , Luísa Lima , Fang Zhao , Joao Barros , Muriel Medard , Ralf Koetter , Ton Kalker , Keesook Han

Implementations of SGD on distributed systems create new vulnerabilities, which can be identified and misused by one or more adversarial agents. Recently, it has been shown that well-known Byzantine-resilient gradient aggregation schemes…

Machine Learning · Computer Science 2022-09-26 Ali Ramezani-Kebrya , Iman Tabrizian , Fartash Faghri , Petar Popovski

Federated learning (FL) is recognized as a key enabling technology to provide intelligent services for future wireless networks and industrial systems with delay and privacy guarantees. However, the performance of wireless FL can be…

Information Theory · Computer Science 2021-05-25 Shaoming Huang , Yong Zhou , Ting Wang , Yuanming Shi

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Cryptography and Security · Computer Science 2021-01-21 Ximing Qiao , Yuhua Bai , Siping Hu , Ang Li , Yiran Chen , Hai Li

Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural…

Cryptography and Security · Computer Science 2016-11-16 Keith Bonawitz , Vladimir Ivanov , Ben Kreuter , Antonio Marcedone , H. Brendan McMahan , Sarvar Patel , Daniel Ramage , Aaron Segal , Karn Seth

Adversarial attacks attempt to disrupt the training, retraining and utilizing of artificial intelligence and machine learning models in large-scale distributed machine learning systems. This causes security risks on its prediction outcome.…

Cryptography and Security · Computer Science 2021-09-07 Yusen Wu , Hao Chen , Xin Wang , Chao Liu , Phuong Nguyen , Yelena Yesha

To preserve user privacy in recommender systems, federated recommendation (FR) based on federated learning (FL) emerges, keeping the personal data on the local client and updating a model collaboratively. Unlike FL, FR has a unique sparse…

Cryptography and Security · Computer Science 2025-01-09 Zhongjian Zhang , Mengmei Zhang , Xiao Wang , Lingjuan Lyu , Bo Yan , Junping Du , Chuan Shi

Smart meter measurements, though critical for accurate demand forecasting, face several drawbacks including consumers' privacy, data breach issues, to name a few. Recent literature has explored Federated Learning (FL) as a promising…

Cryptography and Security · Computer Science 2023-03-29 Muhammad Akbar Husnoo , Adnan Anwar , Nasser Hosseinzadeh , Shama Naz Islam , Abdun Naser Mahmood , Robin Doss

Federated learning (FL) enables multiple clients to collaboratively train a global model without sharing their local data. Recent studies have highlighted the vulnerability of FL to Byzantine attacks, where malicious clients send poisoned…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-16 Kai Yue , Richeng Jin , Chau-Wai Wong , Huaiyu Dai

Federated learning (FL), an emerging distributed machine learning paradigm, has been applied to various privacy-preserving scenarios. However, due to its distributed nature, FL faces two key issues: the non-independent and identical…

Machine Learning · Computer Science 2024-10-18 Youpeng Li , Xinda Wang , Fuxun Yu , Lichao Sun , Wenbin Zhang , Xuyu Wang

This paper proposes a general spectral analysis framework that thwarts a security risk in federated Learning caused by groups of malicious Byzantine attackers or colluders, who conspire to upload vicious model updates to severely debase…

Cryptography and Security · Computer Science 2022-11-28 Hanlin Gu , Lixin Fan , Xingxing Tang , Qiang Yang

Training of large scale models on distributed clusters is a critical component of the machine learning pipeline. However, this training can easily be made to fail if some workers behave in an adversarial (Byzantine) fashion whereby they…

Machine Learning · Computer Science 2021-03-05 Konstantinos Konstantinidis , Aditya Ramamoorthy

Distributed learning has become a necessity for training ever-growing models by sharing calculation among several devices. However, some of the devices can be faulty, deliberately or not, preventing the proper convergence. As a matter of…

Machine Learning · Computer Science 2022-02-08 Jason Akoun , Sebastien Meyer

This paper investigates the robustness of over-the-air federated learning to Byzantine attacks. The simple averaging of the model updates via over-the-air computation makes the learning task vulnerable to random or intended modifications of…

Machine Learning · Computer Science 2022-06-24 Houssem Sifaou , Geoffrey Ye Li
‹ Prev 1 3 4 5 6 7 10 Next ›