Central AsianResearch Index

INTELLIGENT METHODS FOR AUTOMATIC INTRUSION DETECTION MODEL CONSTRUCTION IN INFORMATION SYSTEMS

The ar cle presents a set of tools that can be applied to various sources of audit data to create models of intrusion detec on. The central element of this approach is to apply to the program methods Data Mining are widely collected data audi ng to automa cally construct models of intrusion detec on that accurately capture the actual behavior (such as templates) intrusions and normal ac vi es. This approach greatly reduces the need for manual coding and analysis models of intrusion, as well as insight in the choice of sta s cal indicators to profiles of normal use. Today’s internets are made up of nearly half a million different networks. In any network connec on, iden fying the a acks by their types is a difficult task as different a acks may have various connec ons, and their number may vary from a few to hundreds of network connec ons. To solve this problem, a novel hybrid network IDS called NID-Shield is proposed in the manuscript that classifies the dataset according to different a ack types. Furthermore, the a ack names found in a ack types are classified individually helping considerably in predic ng the vulnerability of individual a acks in various networks. The hybrid NID Shield NIDS applies the efficient feature subset selec on technique called CAPPER and dis nct machine learning methods. The UNSW-NB15 and NSL-KDD datasets are u lized for the evalua on of metrics. Machine learning algorithms are applied for training the reduced accurate and highly merit feature subsets obtained from CAPPER and then assessed by the cross-valida on method for the reduced a ributes. Various performance metrics show that the hybrid NID-Shield NIDS applied with the CAPPER approach achieves a good accuracy rate and low FPR on the UNSW-NB15 and NSL-KDD datasets and shows good performance results when analyzed with various approaches found in exis ng literature studies. Research in network security is a vastly emerging topic in the domain of computer networking due to the ever-increasing density of advanced cybera acks. The intrusion detec on systems (IDSs) are designed to avert the intrusions and to protect the programs, data, and illegi mate access of the computer systems. The IDSs can classify the intrinsic and extrinsic intrusions in the computer networks of an organiza on and ins gate the alarm if security infringement is comprised in an organiza on network

Сведения

Опубликовано
2023 · № 8 (20)
Источник
cyberleninka.ru
Язык
Английский
Издатель
Central Asian Research Journal (CARJIS) ALFRAGANUS universiteti, Бухоро давлат тиббиёт институти