International Journal Of Imaging

Abstract

Feature Selection in DRL Based Malicious URL Detection

Author: P.AshrithReddy, K. Balaji , K.Shruthik ,M Ramesh

Abstract:

Datatheftthroughwebapplicationsthatemulatelegitimateplatforms constitutes a major network security issue. Countermeasures using artificial intelligence (AI)-based systems are often applied because they can effectively detect malicious websites, which are extremely outnumbered bylegitimate ones. In this domain, deep reinforcement learning(DRL)emerges as an attractive field for the developmentof networkintrusiondetectionmodels,eveninthecaseofhighlyskewed classdistributions. However, DRLrequires trainingtimethat increases withdatacomplexity.ThispapercombinesaDRL-basedclassifierwith state-of-the-artfeatureselectiontechniquestospeeduptrainingwhile retaining or even improving classification performance. Our experimentsusedtheMendeleydatasetandfivedifferentstatisticaland correlation-basedfeature-rankingstrategies.Theresultsindicatedthat the selection technique based on the calculation of the Gini index reduces the number of columns in the dataset by 27%, saving more than 10% of