Search Results

Phishing Attacks Continue To Be One Of The Most Prevalent And Damaging Forms Of Cybercrime, Exploiting Human Trust To Steal Sensitive Information Such As Login Credentials, Financial Data, And Personal Identities. Traditional Blacklist-based Approaches Often Fail To Detect Newly Generated Or Obfuscated Phishing Websites, Necessitating More Adaptive And Intelligent Detection Mechanisms. This Work Proposes A Machine Learning–driven Phishing Detection System Integrated With The Flask Web Framework To Provide A Lightweight, Real-time, And User-friendly Application. Features Such As URL Characteristics, HTML And JavaScript Properties, And Domain-related Attributes Are Extracted And Used To Train Classification Models Capable Of Distinguishing Between Legitimate And Phishing Websites. The Trained Model Is Then Deployed Through Flask, Enabling Users To Input URLs And Receive Instant Detection Results Via A Web Interface. Experimental Results Demonstrate The Effectiveness Of The Proposed System In Achieving High Detection Accuracy And Generalizing Well To Unseen Phishing Attempts. The Integration Of Machine Learning With Flask Enhances Both Usability And Scalability, Making The Solution Practical For Deployment In Real-world Scenarios To Strengthen Defenses Against Phishing Threats.