A hybrid trust model using reinforcement learning and fuzzy logic

Aref, Abdullah; Tran, Thomas

doi:10.1111/coin.12155

Cited by 11 publications

(11 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, the SAT may not be provided by a trustor or may not be trusted by the trustee, thus the following equation can be substituted for Equation (10) to allow the trustee to predict the SAT value for the transaction tra:…”

Section: • X Ymentioning

confidence: 99%

Cluster‐based improvement rates for trust establishment models in single or distributed multi‐agent systems

Templeton

Tran

2022

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Intelligent agents within open and dynamic multi-agent systems are becoming increasingly capable in their decision-making abilities and rely upon the notion of trustworthiness to determine which agents to interact with. To improve the overall performance of How to cite this article: Templeton J, Tran T. Cluster-based improvement rates for trust establishment models in single or distributed multi-agent systems.

show abstract

Section: • X Ymentioning

confidence: 99%

Cluster‐based improvement rates for trust establishment models in single or distributed multi‐agent systems

Templeton

Tran

2022

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…The empirical trust evaluation problem is modeled as a cloud service interactive behavior judgment problem. Aref et al 17 proposed a hybrid trust model based on reinforcement learning and fuzzy logic, which uses fuzzy logic to summarize trust factors and uses reinforcement learning to evaluate trust. Kurdi et al 18 proposed a lightweight trust management algorithm based on subjective logic, which improves the TNA‐SL algorithm to make it more suitable for overlaying trust relationships in a cloud environment.…”

Section: Related Workmentioning

confidence: 99%

A trust management model based on mutual trust and a reward‐with‐punishment mechanism for cloud environments

Guo

Yang

Luan

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

Aiming at overcoming problems such as malicious entities and trust crises in cloud environments, a trust management model based on mutual trust and a rewardwith-punishment mechanism is proposed in this paper. First, according to reputation values of entities and trust relationships among entities, we calculate the comprehensive trust values of a service request user to several candidate service providers and probe these providers with high comprehensive trust values. Second, we select a trade provider according to mutual trust. Finally, after the trade, we update the reputation values and other data of the request user, trade provider, and recommenders based on the final trade result to reward or punish them to various degrees, thus ultimately reducing malicious or dishonest behavior. The experimental results show that our model can effectively identify malicious entities to increase the trade success rate. K E Y W O R D Scloud environment, mutual trust, reputation, reward-with-punishment INTRODUCTIONCloud computing is a new network application model that was proposed by Google in 2006. Cloud computing was developed based on a series of traditional technologies, such as grid computing, distributed systems, peer to peer (P2P), and virtualization. It is a new information technology service resource. It distributes computing tasks over a resource pool that is composed of many computers, thereby enabling various application systems to obtain computing power, storage space, and information services as needed and providing dynamically scalable and cheap computing services on demand through the network. 1,2 Cloud computing can be divided into the following three categories according to the service model: IaaS (infrastructure as a service), PaaS (platform as a service), and SaaS (software as a service). 3 However, the widespread application of cloud computing technology also faces many security threats, such as privacy theft, resource misappropriation, virus attacks, and user malicious behavior attacks. The cloud environment is open, and users can add, delete, modify, and check data through the network. If users who passed the identity authentication behave maliciously, a major challenge will be posed to cloud computing security. Therefore, each user's behavior must be evaluated to identify the malicious users.In addition, there is a crisis of trust between cloud service providers and users: Users have doubts regarding whether cloud service providers can provide qualified cloud services in trade (in this paper, when a user buys and uses a provider's service, we say there is a εtradeε between the user and the provider, and the provider is called the trade provider.), while providers also have doubts about users. Therefore, to ensure the smooth operation of trades, the trust relationship between users and providers must be evaluated. Although researchers have proposed various trust models, most models consider only the attitude of user in the trade and ignore that of provider, or do not consider the impact of trade prices ...

show abstract

“…They used Q-learning to evaluate trust to enhance the response of a trust model to dynamic changes in the multi-agent systems. Then they [Aref and Tran 2017] proposed another method based on the previous trust evaluation method, which combines fuzzy logic and the Q-learning algorithm. It is conducive to embody the ambiguity and uncertainty of trust.…”

Section: Models With Discrete Numeralmentioning

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

A hybrid trust model using reinforcement learning and fuzzy logic

Cited by 11 publications

References 57 publications

Cluster‐based improvement rates for trust establishment models in single or distributed multi‐agent systems

Cluster‐based improvement rates for trust establishment models in single or distributed multi‐agent systems

A trust management model based on mutual trust and a reward‐with‐punishment mechanism for cloud environments

A Survey on Trust Evaluation Based on Machine Learning

Contact Info

Product

Resources

About