RETRATCED ARTICLE: Network intrusion detection system using ANFIS classifier

• Published in: Soft computing (Berlin, Germany) Vol. 27; no. 3; pp. 1629 - 1638
• Main Authors: Sajith, P. J., Nagarajan, G.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2023; Springer Nature B.V
• Subjects: Adaptive systems; Artificial Intelligence; Artificial neural networks; Classification; Computational Intelligence; Control; Data mining; Datasets; Engineering; Focus; Fuzzy logic; Intrusion detection systems; Mathematical Logic and Foundations; Mechatronics; Robotics; Artificial neural network; Adaptive neuro-fuzzy inference system; Intrusion detection system; Genetic network programming
• ISSN: 1432-7643; 1433-7479
• DOI: 10.1007/s00500-022-06854-x

As network security had really become a basic issue, there is been a lot of improvement in designs for past years. Among several designs, IDS is one of the greatest hits . It has all of the stores of being that the presence of inadequacy and the dubious considered the impedances make fuzzy developments sensible for such structures. Fuzzy plans are not regularly versatile and do not have the ability to make models solely subject to the goal structure's model data. So, this paper aims in using Adaptive Neuro-Fuzzy Inference System (ANFIS) as a classifier for classifying the networks as malicious categories (Probe, DoS, U2R, R2L) and normal on DARPA 1999 database and are evaluated with other models like Fuzzy GNP, HHO in which experimental results show that ANFIS show better performance because it joins the upsides of both ANN and fuzzy deduction frameworks including the capacity to catch the nonlinear design of interaction, variation ability, and fast learning limit.