Browsing by Author "Mayadunna, H"

Now showing 1 - 2 of 2

Embargo
Improving trusted routing by identifying malicious nodes in a MANET using reinforcement learning
(IEEE, 2017-09-06) Mayadunna, H; De Silva, S. L; Wedage, L; Pabasara, S; Rupasinghe, L; Liyanapathirana, C; Kesavan, K; Nawarathna, C; Sampath, K. K
Mobile ad-hoc networks (MANETs) are decentralized and self-organizing communication systems. They have become pervasive in the current technological framework. MANETs have become a vital solution to the services that need flexible establishments, dynamic and wireless connections such as military operations, healthcare systems, vehicular networks, mobile conferences, etc. Hence it is more important to estimate the trustworthiness of moving devices. In this research, we have proposed a model to improve a trusted routing in mobile ad-hoc networks by identifying malicious nodes. The proposed system uses Reinforcement Learning (RL) agent that learns to detect malicious nodes. The work focuses on a MANET with Ad-hoc On-demand Distance Vector (AODV) Protocol. Most of the systems were developed with the assumption of a small network with limited number of neighbours. But with the introduction of reinforcement learning concepts this work tries to minimize those limitations. The main objective of the research is to introduce a new model which has the capability to detect malicious nodes that decrease the performance of a MANET significantly. The malicious behaviour is simulated with black holes that move randomly across the network. After identifying the technology stack and concepts of RL, system design was designed and the implementation was carried out. Then tests were performed and defects and further improvements were identified. The research deliverables concluded that the proposed model arranges for highly accurate and reliable trust improvement by detecting malicious nodes in a dynamic MANET environment.
Embargo
A trust evaluation model for online social networks
(IEEE, 2018-10-02) Mayadunna, H; Rupasinghe, L
With the rapid prevalence of online social networks, the trustworthiness of online users has become a current issue in the field of social computing. The evaluation of trust in social networks has been widely used in situations such as friend-recommendation, e-commerce and trust based access control systems. Security is the backbone of social networks. For sharing and exchanging of information between the trusted users only trustworthiness of the user needs to be determined. One of the key requirements in trust applications is recognizing the trustworthy actors in the network. In the proposed research, a general trust framework will be introduced to calculate the node trust values for social network users by applying reinforcement learning methods. Firstly, some selected features of social network are used as the training feature and the measurement whether there is an edge between nodes used as label information. Secondly, a training model will be used to calculate the node trust value. Then a recommendation algorithm will be used to calculate node trust score. Finally, the simulation is used to verify the performance of suggested method. For the simulation of experimentation, data from an adaptive social network will be used.