Enhanced MANET Security using Artificial Immune System Based Danger Theory to Detect Selfish Nodes

2021 ◽  
pp. 102538
Author(s):  
Lincy E. Jim ◽  
Nahina Islam ◽  
Mark A. Gregory
Author(s):  
Lincy Elizebeth Jim ◽  
Mark A Gregory

In Mobile Ad hoc Networks (MANETs) the nodes act as a host as well as a router, thereby forming a self-organizing network that does not rely upon fixed infrastructure, other than gateways to other networks. Security is important for MANETs and trust computation is used to improve collaboration between nodes. This paper proposes an Artificial Immune System-based reputation (AISREP) algorithm to compute trust and thereby provide a resilient reputation mechanism. In this paper, the presence of selfish nodes are considered. Selfish nodes are known to enhance the reputation of their selfish peers which in turn causes packet loss. In the event of the packet being routed using the AISREP algorithm, even though the number of selfish nodes increases, this algorithm identifies the selfish nodes and avoids using the selfish nodes from the routing path thereby improving the overall performance of the network.


Author(s):  
Ali Raza ◽  
Benito R. Fernandez

Artificial immune system draws its inspiration from the biological immune functions mainly those of humans. Recently, newer definitions of biological immune system have appeared and gained significance because of their strong immunological roots e.g. danger theory. This raises the need to look into earlier work on immuno-inspired robotics. Especially, older approach of idiotypic-network must be compared with the newer approach of danger-theory. Authors in this research have successfully applied both the definitions on heterogeneous mobile robotic systems. Idiotypic connections between antibodies have been used as a tool to navigate robots as well as to establish inter-robot communication in an immune network approach. Similarly, co-stimulatory signal concentrations have been used to contextualize the environment, in a danger theory approach, to initiate and regulate the immuno responses. Immune metaphors have been translated into relevant computational models and simulated in search and rescue operation in an obstacle filled arena.


Web Mining ◽  
2011 ◽  
pp. 145-168 ◽  
Author(s):  
Andrew Secker ◽  
Alex A. Freitas ◽  
Jon Timmis

The natural immune system exhibits many properties that are of interest to the area of Web mining. Of particular interest is the dynamic nature of the immune system when compared with the dynamic nature of mining information from the Web. As part of a larger project to construct a large-scale dynamic Web-mining system, this chapter reports initial work on constructing an e-mail classifier system. The Artificial Immune System for e-mail Classification (AISEC) is described in detail and compared with a traditional approach of naive Bayesian classification. Results reported compare favorably with the Bayesian approach and this chapter highlights how the Danger Theory from immunology can be used to further improve the performance of such an artificial immune system.


Sign in / Sign up

Export Citation Format

Share Document