Book ChapterDOI
PDGAN: A Novel Poisoning Defense Method in Federated Learning Using Generative Adversarial Network
Ying Zhao,Junjun Chen,Jiale Zhang,Di Wu,Jian Teng,Shui Yu +5 more
- pp 595-609
Reads0
Chats0
TLDR
A novel poisoning defense generative adversarial network (PDGAN) is proposed to defend the poising attack of poisoning attacks in federated learning.Abstract:
Federated learning can complete an enormous training task efficiently by inviting participants to train a deep learning model collaboratively, and the user privacy will be well preserved for the users only upload model parameters to the centralized server. However, the attackers can initiate poisoning attacks by uploading malicious updates in federated learning. Therefore, the accuracy of the global model will be impacted significantly after the attack. To address this vulnerability, we propose a novel poisoning defense generative adversarial network (PDGAN) to defend the poising attack. The PDGAN can reconstruct training data from model updates and audit the accuracy for each participant model by using the generated data. Precisely, the participant whose accuracy is lower than a predefined threshold will be identified as an attacker and model parameters of the attacker will be removed from the training procedure in this iteration. Experiments conducted on MNIST and Fashion-MNIST datasets demonstrate that our approach can indeed defend the poisoning attacks in federated learning.read more
Citations
More filters
Journal ArticleDOI
A survey on security and privacy of federated learning
Viraaji Mothukuri,Reza M. Parizi,Seyedamin Pouriyeh,Yan Huang,Ali Dehghantanha,Gautam Srivastava,Gautam Srivastava +6 more
TL;DR: This paper aims to provide a comprehensive study concerning FL’s security and privacy aspects that can help bridge the gap between the current state of federated AI and a future in which mass adoption is possible.
Journal ArticleDOI
Federated learning review: Fundamentals, enabling technologies, and future applications
TL;DR: Federated Learning (FL) has been foundational in improving the performance of a wide range of applications since it was first introduced by Google and some of the most prominent and commonly used FL-powered applications are Android's Gboard for predictive text and Google Assistant as mentioned in this paper .
Journal ArticleDOI
Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
Nuria Rodr'iguez-Barroso,Daniel Jim'enez L'opez,M. V. Luz'on,Francisco Herrera,Eugenio Martínez-Cámara +4 more
TL;DR: In this article , the authors present an extensive review of the threats of federated learning, as well as their corresponding countermeasures, attacks versus defences, and expound guidelines for selecting the most adequate defence method according to the category of the adversarial attack.
Journal ArticleDOI
Zero Knowledge Clustering Based Adversarial Mitigation in Heterogeneous Federated Learning
TL;DR: The proposed ZeKoC approach, a Zero Knowledge Clustering approach to mitigating adversarial attacks, successfully mitigates general attacks while outperforming state-of-art schemes.
Journal ArticleDOI
A Systematic Literature Review on Federated Machine Learning: From A Software Engineering Perspective
TL;DR: In this article, the authors perform a systematic literature review from a software engineering perspective, based on 231 primary studies, covering the lifecycle of federated learning system development that includes background understanding, requirement analysis, architecture design, implementation, and evaluation.
References
More filters
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Posted Content
Communication-Efficient Learning of Deep Networks from Decentralized Data
TL;DR: This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.
Posted Content
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
TL;DR: Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits.
Proceedings Article
Communication-Efficient Learning of Deep Networks from Decentralized Data
TL;DR: In this paper, the authors presented a decentralized approach for federated learning of deep networks based on iterative model averaging, and conduct an extensive empirical evaluation, considering five different model architectures and four datasets.