Cluster-level trust prediction based on multi-modal social networks

Zhang, Weiyu; Wu, Bin; Liu, Yang

doi:10.1016/j.neucom.2016.01.108

Cited by 10 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, supervised learning must have labeled data to train the model, in most ZTA practical application scenarios, users and devices features lack clear labels, and unsupervised learning such as K-means [90,162,96,154] can solve this problem by clustering trust objects without label into different level of trust groups. To further improve unsupervised learning performance, semi-supervised learning, which combines supervised and unsupervised learning, can be used to optimize the clustering boundaries.…”

Section: Experience-driven Trust Evaluationmentioning

confidence: 99%

Automation and Orchestration of Zero Trust Architecture:Potential Solutions and Challenges

Cao¹,

Pokhrel²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>Zero Trust Architecture (ZTA) is a paradigm shift in how we protect data, stay connected, and access resources. ZTA is non-perimeter based defense, which has been emerging as a promising revolution in the cybersecurity field. It can be used to continuously maintain security by safeguarding against attacks both from inside and outside of the network system. However, automation and orchestration ZTA, an essential direction towards its seamless deployments over real-word networks, have been poorly understood in literature. In this paper, we first identify the bottlenecks, discuss the background of ZTA and compare it with traditional perimeter-based security architectures. More importantly, we present a comprehensive direction towards the automation and orchestration of ZTA by employing AI techniques. In other words, the key potential and roles of celebrates AI techniques for the automation and orchestration of ZTA are demonstrated for further exploration. Overall, in this review paper, we develop a foundational view on the challenges and potential enablers for the automation and orchestration of ZTA.</p>

show abstract

Section: Experience-driven Trust Evaluationmentioning

confidence: 99%

Automation and Orchestration of Zero Trust Architecture:Potential Solutions and Challenges

Cao¹,

Pokhrel²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…They can be utilized to process data for trust evaluation. For example, in the absence of trust attribute information, machine learning is used to cluster similar users according to user attributes, and then for those users lacking trust information, trust evaluation is performed with the trust data of the user that does not lack trust information [Zhang et al 2016].…”

Section: Machine Learning Algorithms For Assisting Trustmentioning

confidence: 99%

“…There is no discussion on computational overhead. Zhang et al [2016] offered a method of trust prediction on the basis of co-cluster to mitigate the sparseness of an explicit trust graph and improve its ability to predict trust. They graphically represented social networks with users and items and utilized the users' rating on items and the relationship between the users to predict trust.…”

Section: :13mentioning

confidence: 99%

A Survey on Trust Evaluation Based on Machine Learning

et al. 2020

View full text Add to dashboard Cite

Trust evaluation is the process of quantifying trust with attributes that influence trust. It faces a number of severe issues such as lack of essential evaluation data, demand of big data process, request of simple trust relationship expression, and expectation of automation. In order to overcome these problems and intelligently and automatically evaluate trust, machine learning has been applied into trust evaluation. Researchers have proposed many methods to use machine learning for trust evaluation. However, the literature still lacks a comprehensive literature review on this topic. In this article, we perform a thorough survey on trust evaluation based on machine learning. First, we cover essential prerequisites of trust evaluation and machine learning. Then, we justify a number of requirements that a sound trust evaluation method should satisfy, and propose them as evaluation criteria to assess the performance of trust evaluation methods. Furthermore, we systematically organize existing methods according to application scenarios and provide a comprehensive literature review on trust evaluation from the perspective of machine learning's function in trust evaluation and evaluation granularity. Finally, according to the completed review and evaluation, we explore some open research problems and suggest the directions that are worth our research effort in the future.

show abstract

“…These models are defined based on the researchers experience and require an intensive manual engineering. Moreover, these approaches usually require a time consuming preprocessing phase such as computation of global trust [20], execution of a Principal Component Analysis (PCA) [21] or finding all the paths between two nodes to calculate their similarity [22]. These calculations might be feasible for a small network graph, but not for a large graph dataset [18].…”

Section: Introductionmentioning

confidence: 99%

dTrust: A Simple Deep Learning Approach for Social Recommendation

Dang

Ignat

2017

2017 IEEE 3rd International Conference on Collaboration and Internet Computing (CIC)

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. dTrust: a simple deep learning approach for social recommendationQuang-Vinh Dang, Claudia-Lavinia IgnatTo cite this version: Abstract-Rating prediction is a key task of e-commerce recommendation mechanisms. Recent studies in social recommendation enhance the performance of rating predictors by taking advantage of user relationships. However, these prediction approaches mostly rely on user personal information which is a privacy threat.In this paper, we present dTrust, a simple social recommendation approach that avoids using user personal information. It relies uniquely on the topology of an anonymized trust-useritem network that combines user trust relations with user rating scores. This topology is fed into a deep feed-forward neural network. Experiments on real-world data sets showed that dTrust outperforms state-of-the-art in terms of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores for both warmstart and cold-start problems.

show abstract

Cluster-level trust prediction based on multi-modal social networks

Cited by 10 publications

References 42 publications

Automation and Orchestration of Zero Trust Architecture:Potential Solutions and Challenges

Automation and Orchestration of Zero Trust Architecture:Potential Solutions and Challenges

A Survey on Trust Evaluation Based on Machine Learning

dTrust: A Simple Deep Learning Approach for Social Recommendation

Contact Info

Product

Resources

About