Logo image
SVM based generative adverserial networks for federated learning and edge computing attack model and outpoising
Journal article   Peer reviewed

SVM based generative adverserial networks for federated learning and edge computing attack model and outpoising

M. Poongodi, Ranjan Walia, Celestine Iwendi, Tariq Ahamed Ahanger, S.T Suganthi, M. M Kamruzzaman, S. Bourouis, Wajdi Alhakami and Mounir Hamdi
Expert Systems, Vol.40(5), e13072
09/08/2022

Abstract

poisoning attack Generative AdversarialNetwork Federated learning Edge Computing
Machine learning algorithms are prone to attacks: An attackers can use the malicious nodes to attack the training dataset to manipulate the process of learning and reduce the efficiency of the algorithm working performance. Optimal poisoning attacks have already been proposed to evaluate worst case scenarios, modelling attacks as a bilevel optimization problem. Solving these problems is computationally demanding and has limited applicability for some models such as deep networks. In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers generating adversarial training examples, i.e. samples that look like genuine data points but that reduce the accuracy of the classifier in the process of training process. The proposed system have 3 components of Generative Adverserial networks (GAN) generator, discriminator, and the target classifier. The proposed system allows to detect the vulnerability easy and it can be found as similar as realistic attacks to detect the area where the underlying data distribution have more possibility of poising attack which cause vulnerability to the network. Our experimentation, proves the claim our that the proposed model is effective on compromising the classifiers uses the machine learning algorithms and also deep learning networks.
url
Link to Published VersionView
Published (Version of record)Publisher sites may require subscription to read content

Metrics

4 File views/ downloads
49 Record Views
45 Times Cited - Scopus

Details

Logo image

Usage Policy