An intelligent approach based on neuro-fuzzy detachment scheme for preventing jamming attack in wireless networks

Abstract

Securing information systems and the networks that connect them is paramount in the age of growing incidents of cyber attacks. Invasive and continuous cyber attacks on information systems continue to create a potentially shocking blow to the transmission of information from one end to the other. Wireless networks are often vulnerable to intentional interference physical layer reactive jamming attacks, in which the adversaries effectively and stealthily corrupt the packet by injecting high level of noise thereby keeping the channel busy. Consequently, legitimate traffic gets completely blocked; resulting in packet loss at the receiver side. These jammers cause serious threat to wireless communication and they are difficult to identify. A novel method known as 'Neuro Fuzzy Detachment Scheme' has been proposed to prevent such sophisticated and powerful jamming attack.The key idea is to identify and detach jammers from the network to ensure perspicuous transmission. The proposed detachment scheme operates in three modules. In module one, the past record log files are analyzed to extract the trust values for different traces. Using the extracted trust values, the decision factors are monitored for different runs with the attacker in between the communication range of source and the sink and then the suspicious traces are identified and classified using ANFIS classifier. In module two, to trace abnormality, three reorganizing algorithms have been developed to reorganize the categorized traces. In module three, misbehaving nodes are identified and detached from the network. It is observed through simulation studies that the proposed scheme attains higher throughput and packet delivery ratio while attaining lower delay.

Securing jammed network using reliability behavior value through neuro-fuzzy analysis

“…But these works do not help in performing both direct and indirect observations as well as do not calculate the reliability of nodes in the communication path, which is different from the problem of finding the network activities that are associated with an attack. Ratna et al (2014) in the previous work have proposed Neuro Fuzzy Detachment Scheme to prevent reactive jamming attack that targets the physical layer of the wireless network. In this scheme, the malicious node is identified based on the trust values obtained from its route path maintained at the previous history log files.…”

“…In the fourth experiment, figure 6a, b and c shows the results of No Attack, No Defence, prevention using researcher's Earlier MMMTR Approach (Ratna et al 2014), and the Proposed system with HBR Approach for different number of MJN.…”

Improved Beetle Antennae Algorithm Based on Localization for Jamming Attack in Wireless Sensor Networks

“…Rantna, et al proposed a neuro fuzzy disengagement scheme to prevent interference attacks in a WSN, ensuring data transmission by separating the malicious nodes. This method has high throughput and packet delivery ratio (PDR), low latency, but high overhead [8]. Recently, Hu et al, proposed centroid localization (CL), CL algorithm is an algorithm that calculates the centroid of the polygon composed of anchor nodes sending information as the coordinate position of unknown nodes, but the positioning accuracy is low [9].…”