Template-Type: ReDIF-Article 1.0
Author-Name:Rimsha Jamil Ghilzai, Hafiz Gulfam Ahmad Umer, Urwa Bibi, Muskan Maryam
Author-Email:darkshadowsrj@gmail.com
Author-Workplace-Name:Ghazi University D.G.Khan
Title:AI-Sentinel:ANovelAI-PoweredIntrusionDetection ApproachAgainstCyberThreatsforIn-Vehicular Communication Systems
Abstract:The emergence of revolutionizingtechnologiessuchasArtificialIntelligenceandthe InternetofThings,andtheirintegrationintotheautomotiveindustryhas brought innovationsandmadethelivesofcommonpeopleeasierandmorecomplacent. Leveragingtheadvancedintelligentservicesprovidedbyconnectedandautonomousvehicles, thedrivingexperienceismuchmoreconvenientandeffortless.TheCAN(ControllerArea Network)protocolisthemostdeployedprotocolinin-vehicularcommunicationsintheICVs (intelligentconnectedvehicles)environmentduetoitsefficiencyandspeed.However,itlacks basicsecurity mechanismslike encryptionandauthentication, making it vulnerable tovarious cyberthreats.Inthisarticle,wehavepresentedanovel,robust,cutting-edgeAI-based Intrusion detection systemfordetecting various seen and unseen cyber-attacks in in-vehicular networkstoensuresecurity.TwomainmodelsdeployedintheproposedframeworkareRNN fordealingwithtemporaldependenciesintheCANtrafficandLightGBMforefficientfeature extraction. The experimental resultsshow that the hybridofthese two models performs better intermsofvariousevaluationmetrics,withitsaccuracybeing94%inclassifyingtheCAN traffic intonormal anddifferentattack classes. A comparisonwiththe existingstate-of-the-art approachesshowsthatourproposedapproachismorerobustandsecure,withitbeingdeployedinaFederated LearningFLenvironment.
Keywords:Intrusiondetection;IDS,IVN;In-vehicularcommunication;ML;DL;Cyber-attacks;CANbus;FederatedLearning(FL);Intelligentconnectedvehicles(ICVs)
Journal:International Journal of Innovations in Science and Technology
Pages:1200-1224
Volume:7
Issue:2
Year:2025
Month:June
File-URL:https://journal.50sea.com/index.php/IJIST/article/view/1417/1953
File-Format: Application/pdf
File-URL:https://journal.50sea.com/index.php/IJIST/article/view/1417
File-Format: text/html
Handle: RePEc:abq:IJIST:v:7:y:2025:i:2:p:1200-1224