Fuzzy Logic based Man-in-the-Middle Attack Detection Scheme in Advanced Metering Infrastructure

Man-in-the-middle attack in advanced metering infrastructure allows intruders to monitor and manipulate communications among legitimate users, which poses a crucial threat to network security. The traditional signature based intrusion detection schemes involves large number of rules that imposes computational complexity on resource constraint devices. Further, the conventional intrusion detection schemes are used for binary classification where severity of the threat based solutions cannot be achieved. To evade this, fuzzy logic based intrusion detection scheme that incorporates various subnets of internet protocol addressing and mac addresses as input and decision on the severity of threat as output. The attack is emulated using Ettercap and the packet information is captured using Wireshark. The data is pre-processed and the input term sets with predefined ranges and membership functions are derived. The fuzzy rules are framed to identify the vulnerability level based on the fuzzy sets assigned to the internet protocol and media access control addresses. The proposed fuzzy based intrusion detection scheme is implemented in Python. The results exhibit that the proposed fuzzy based scheme exhibits its efficiency.