Peer-to-peer trust management in intelligent transportation system: An Aumann’s agreement theorem based approach

Ramesh, R.; Vijayaragavan, M.; Poongodi, M.; Hamdi, Mounir; Bourouis, Sami

doi:10.1016/j.icte.2022.02.004

Cited by 25 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We investigate the setting for the adversary network for the poison attack, the assumption, the first case, taken as perfect knowledge gained by the adversary on the target classifier ( P TC ) and known feature space t ( x ).The second case, is that adversaries gained the less or limited knowledge ( L TC ), target classifier. We assumed that attacker may have knowledge of features representation, but not the training dataset (Rathore et al, 2022; Poongodi, Bourouis et al, 2022; Ramesh, Lihore et al, 2022; Poongodi, Malviya, Hamdi et al, 2022; Poongodi, Malviya, Kumar et al, 2022; Poongodi, Hamdi, & Wang 2022; Poongodi et al, 2021; Ramesh, Vijayaragavan et al, 2022; Hamdi et al, 2022; Poongodi, Hamdi, Malviya et al, 2022; Kamruzzaman 2021; Hossain et al, 2022; Chen et al, 2019; Kamruzzaman 2013, 2014; Zhang et al, 2021; Hossain, Kamruzzaman et al, 2022; Sarker et al, 2021; Shi et al, 2020; Chen et al, 2020).…”

Section: Attack Modelsmentioning

confidence: 99%

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

Machine learning are vulnerable to the threats. The Intruders can utilize the malicious nature of the nodes to attack the training dataset to worsen the process and manipulate the learning and make the over all system with less efficiency and performance. The optimized poison attack procedures are already introduced to estimate the overall bad scenario, design the intrusion as bi‐level optimization and it is considered computational complexity is high and demanding, in contrary the applicability is limited such models deep neural networks. In this research papers, we have proposed, novel proposed system, poisoning attacks against the Machine learning training dataset, including the genuine data points that reduce the accuracy of the classifier in the process of training. 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.

show abstract

Section: Attack Modelsmentioning

confidence: 99%

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…When different models produce consistent results, it indicates that they have a similar understanding of the categories and can be expected to perform consistently [14,37]. Notwithstanding, it is imperative to consider that attaining agreement does not invariably guarantee validity; nevertheless, it is probable that they would agree on reliable samples to a greater extent [2,31,37,54]. Whilst our work draws inspiration from the aforementioned approaches, our fundamental aim is to address the issue of noisy label image classification through the application of a novel sample selection.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, clean data are likely to have high predictive probability agreement in (1). According to the theory of peer classifier agree-ment [24,54,61], it is advisable that clean data should be selected based on high peer classifier agreement, but noisy data should be cautiously selected based on low peer classifier agreement. Leveraging the aforementioned remark, we partition the training set D into the clean set Dclean and noisy set Dnoisy using the cosine similarity in (1).…”

Section: Reliability Based Sample Selectionmentioning

confidence: 99%

PASS: Peer-Agreement based Sample Selection for training with Noisy Labels

Garg¹,

Nguyen²,

Felix³

et al. 2023

Preprint

View full text Add to dashboard Cite

Noisy labels present a significant challenge in deep learning because models are prone to overfitting. This problem has driven the development of sophisticated techniques to address the issue, with one critical component being the selection of clean and noisy label samples. Selecting noisy label samples is commonly based on the small-loss hypothesis or on feature-based sampling, but we present empirical evidence that shows that both strategies struggle to differentiate between noisy label and hard samples, resulting in relatively large proportions of samples falsely selected as clean. To address this limitation, we propose a novel peer-agreement based sample selection (PASS). An automated thresholding technique is then applied to the agreement score to select clean and noisy label samples. PASS is designed to be easily integrated into existing noisy label robust frameworks, and it involves training a set of classifiers in a round-robin fashion, with peer models used for sample selection. In the experiments, we integrate our PASS with several state-of-the-art (SOTA) models, including InstanceGM, DivideMix, SSR, FaMUS, AugDesc, and C2D, and evaluate their effectiveness on several noisy label benchmark datasets, such as CIFAR-100, CIFAR-N, Animal-10N, Red Mini-Imagenet, Clothing1M, Mini-Webvision, and Imagenet. Our results demonstrate that our new sample selection approach improves the existing SOTA results of algorithms.

show abstract

“…Binary scores, i.e., 0 or 1, are not the best indicators to evaluate studies. However, we somewhat followed the authors' method to use fuzzy linear variables [9][10][11][12][13][14][15]. However, instead of using a crisp set, we chose a numeric set ranging from 0 to 4 for each question.…”

Section: Quality Assessment Criteriamentioning

confidence: 99%

Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review

Dhiman¹,

Kaur

Balasaraswathi

et al. 2023

Sustainability

View full text Add to dashboard Cite

Different kinds of techniques are evaluated and analyzed for various classification models for the detection of diseases of citrus fruits. This paper aims to systematically review the papers that focus on the prediction, detection, and classification of citrus fruit diseases that have employed machine learning, deep learning, and statistical techniques. Additionally, this paper explores the present state of the art of the concept of image acquisition, digital image processing, feature extraction, and classification approaches, and each one is discussed separately. A total of 78 papers are selected after applying primary selection criteria, inclusion/exclusion criteria, and quality assessment criteria. We observe that the following are widely used in the selected studies: hyperspectral imaging systems for the image acquisition process, thresholding for image processing, support vector machine (SVM) models as machine learning (ML) models, convolutional neural network (CNN) architectures as deep learning models, principal component analysis (PCA) as a statistical model, and classification accuracy as evaluation parameters. Moreover, the color feature is the most popularly used feature for the RGB color space. From the review studies that performed comparative analyses, we find that the best techniques that outperformed other techniques in their respective categories are as follows: SVM among the ML methods, ANN among the neural network networks, CNN among the deep learning methods, and linear discriminant analysis (LDA) among the statistical techniques.This study concludes with meta-analysis, limitations, and future research directions.

show abstract

Peer-to-peer trust management in intelligent transportation system: An Aumann’s agreement theorem based approach

Cited by 25 publications

References 24 publications

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

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

PASS: Peer-Agreement based Sample Selection for training with Noisy Labels

Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review

Contact Info

Product

Resources

About