English
Related papers

Related papers: Mean Aggregator is More Robust than Robust Aggrega…

200 papers

Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in Internet of Things (IoT) environments, particularly as data poisoning attacks increasingly threaten the integrity of model…

Privacy-preserving federated averaging is a central approach for protecting client privacy in federated learning. In this paper, we study this problem in an asynchronous communications setting with malicious aggregators. We propose a new…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-09 Antonella Del Pozzo , Achille Desreumaux , Mathieu Gestin , Alexandre Rapetti , Sara Tucci-Piergiovanni

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…

Machine Learning · Computer Science 2019-02-25 Gavin Weiguang Ding , Kry Yik Chau Lui , Xiaomeng Jin , Luyu Wang , Ruitong Huang

With the increasing importance of machine learning, the privacy and security of training data have become critical. Federated learning, which stores data in distributed nodes and shares only model parameters, has gained significant…

Machine Learning · Computer Science 2025-07-10 Yang Li , Chunhe Xia , Chang Li , Tianbo Wang

Modern ML applications increasingly rely on complex deep learning models and large datasets. There has been an exponential growth in the amount of computation needed to train the largest models. Therefore, to scale computation and data,…

Machine Learning · Computer Science 2023-09-26 Hamidreza Almasi , Harsh Mishra , Balajee Vamanan , Sathya N. Ravi

Federated learning (FL) enables multiple clients to collaboratively train an accurate global model while protecting clients' data privacy. However, FL is susceptible to Byzantine attacks from malicious participants. Although the problem has…

Cryptography and Security · Computer Science 2023-08-08 Wei Wan , Shengshan Hu , Jianrong Lu , Leo Yu Zhang , Hai Jin , Yuanyuan He

We offer a study that connects robust discriminative classifiers trained with adversarial training (AT) with generative modeling in the form of Energy-based Models (EBM). We do so by decomposing the loss of a discriminative classifier and…

Machine Learning · Computer Science 2023-06-06 Senad Beadini , Iacopo Masi

Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wherein FL clients are subject to adversarial (Byzantine) attacks, while the FL server is trusted…

Machine Learning · Computer Science 2026-04-30 Emmanouil Kritharakis , Dusan Jakovetic , Antonios Makris , Konstantinos Tserpes

Machine learning is susceptible to poisoning attacks, in which an attacker controls a small fraction of the training data and chooses that data with the goal of inducing some behavior unintended by the model developer in the trained model.…

Machine Learning · Computer Science 2023-11-21 Evan Rose , Fnu Suya , David Evans

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

Matching the performance of conditional Generative Adversarial Networks with little supervision is an important task, especially in venturing into new domains. We design a new training algorithm, which is robust to missing or ambiguous…

Machine Learning · Statistics 2019-06-11 Kiran Koshy Thekumparampil , Sewoong Oh , Ashish Khetan

Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in their devices. However, that same autonomy opens the door for…

Cryptography and Security · Computer Science 2022-07-06 Najeeb Moharram Jebreel , Josep Domingo-Ferrer , David Sánchez , Alberto Blanco-Justicia

Conformal prediction has shown impressive capacity in constructing statistically rigorous prediction sets for machine learning models with exchangeable data samples. The siloed datasets, coupled with the escalating privacy concerns related…

Machine Learning · Computer Science 2024-06-05 Mintong Kang , Zhen Lin , Jimeng Sun , Cao Xiao , Bo Li

The rapid development of artificial intelligence systems has amplified societal concerns regarding their usage, necessitating regulatory frameworks that encompass data privacy. Federated Learning (FL) is posed as potential solution to data…

Machine Learning · Computer Science 2025-03-28 Mario García-Márquez , Nuria Rodríguez-Barroso , M. Victoria Luzón , Francisco Herrera

In overhead image segmentation tasks, including additional spectral bands beyond the traditional RGB channels can improve model performance. However, it is still unclear how incorporating this additional data impacts model robustness to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-22 Elise Bishoff , Charles Godfrey , Myles McKay , Eleanor Byler

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

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and…

Machine Learning · Computer Science 2021-02-26 Dong Yin , Yudong Chen , Kannan Ramchandran , Peter Bartlett

Local Differential Privacy (LDP) is now widely adopted in large-scale systems to collect and analyze sensitive data while preserving users' privacy. However, almost all LDP protocols rely on a semi-trust model where users are…

Cryptography and Security · Computer Science 2023-03-21 Rong Du , Qingqing Ye , Yue Fu , Haibo Hu , Jin Li , Chengfang Fang , Jie Shi

In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication constraints. While prior work has developed various robust aggregation rules at the server to enhance robustness to Byzantine…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-01 Chengxi Li , Youssef Allouah , Rachid Guerraoui , Mikael Skoglund , Ming Xiao

Adversarial attacks pose a major challenge to distributed learning systems, prompting the development of numerous robust learning methods. However, most existing approaches suffer from the curse of dimensionality, i.e. the error increases…

Machine Learning · Computer Science 2025-11-19 Wenyu Liu , Tianqiang Huang , Pengfei Zhang , Zong Ke , Minghui Min , Puning Zhao