Reputation-based security model for detecting biased attacks in big data

Abstract

As internet of things (IoT) devices are increasing since the emergence of these devices in 2010, the data stored by these devices should have a proper security measure so that it can be stored without getting in hands of an attacker. The data stored has to be analyzed whether the data is safe or malicious, as the malicious data can corrupt the whole information. The security model in big data has many challenges such as vulnerability to fake data generation, troubles with cryptographic protection, and absent security audits. As cyber attacks are increasing the main objective of each organization is to secure the data efficiently. This paper presents a model of reputation security for the detection of biased attacks on big data. The proposed model provides various evaluation models to identify biased attack in malicious IoT devices and provide a secure communication metric for big data. The results show better rates in terms of attack detection rate, attack detection failure rata, system throughput and number of dead nodes when the attack rate is increased when compared with the existing reputation-based security (ERS) model. Moreover, this model reputation-based biased attack detection (RBAD) increases the security of the IoT devices in the big data and reduces the biased attack coming from various malicious nodes.