Dynamic　web　applications　play　a　vital　role　in　providing　resources　manipulation　and　interaction　between　clients　and　servers.　The　features　presently　supported　by　browsers　have　raised　business　opportunities,　by　supplying　high　interactivity　in　web-based　services,　like　web　banking,　e-commerce,　social　networking,　forums,　and　at　the　same　time,　these　features　have　brought　serious　risks　and　increased　vulnerabilities　in　web　applications　that　enable　cyber-attacks　to　be　executed.　One　of　the　common　high-risk　cyber-attack　of　web　application　vulnerabilities　is　cross-site　scripting　(XSS).　Nowadays,　XSS　is　still　dramatically　increasing　and　considered　as　one　of　the　most　severe　threats　for　organizations,　users,　and　developers.　If　the　ploy　is　successful,　the　victim　is　at　the　mercy　of　the　cybercriminals.　In　this　research,　a　robust　artificial　neural　network-based　multilayer　perceptron　(MLP)　scheme　integrated　with　the　dynamic　feature　extractor　is　proposed　for　XSS　attack　detection.　The　detection　scheme　adopts　a　large　real-world　dataset,　the　dynamic　features　extraction　mechanism,　and　MLP　model,　which　successfully　surpassed　several　tests　on　an　employed　unique　dataset　under　careful　experimentation,　and　achieved　promising　and　state-of-the-art　results　with　accuracy,　detection　probabilities,　false　positive　rate,　and　AUC-ROC　scores　of　99.32%,　98.35　%,　0.3%,　and　99.02%,　respectively.　Therefore,　it　has　the　potentials　to　be　applied　for　XSS-based　attack　detection　in　either　the　client-side　or　the　server-side.