Evolutionary Algorithm with Deep Auto Encoder Network Based Website Phishing Detection and Classification

Website phishing is a cyberattack that targets online users for stealing their sensitive data containing login credential and banking details. The websites appear very similar to equivalent legitimate attracting huge amount of Internet users. attacker fools the user by offering masked webpage as or reliable retrieving its important information. Presently, anti-phishing approaches necessitate experts extract site features utilize third-party services website detection. These techniques have some drawbacks, requirement extracting time consuming. Many solutions attack been presented, such blacklist whitelist, heuristics, machine learning (ML) based approaches, which face difficulty in accomplishing effectual recognition performance due continual improvements technologies. Therefore, this study presents an optimal deep autoencoder network detection classification (ODAE-WPDC) model. proposed ODAE-WPDC model applies input pre-processing at initial stage get rid missing values dataset. Then, feature extraction artificial algae algorithm (AAA) selection (FS) are utilized. DAE with received carried out process, parameter tuning technique was performed using invasive weed optimization (IWO) accomplish enhanced performance. validation tested Phishing URL dataset from Kaggle repository. experimental findings confirm better maximum accuracy 99.28%.