SafeURL Inspector
Members: Siva Satyanarayana Raju Pusapati, Sampath Sai Yelleti, Hemanth Kumar Reddy Tiyyagura, Chandra Kiran Viswanath Balusu, Anusha Bhavanam, Poojasree Keerithipati
The proliferation of counterfeit websites represents a growing concern in the digital landscape, where malicious actors aim to exploit the credibility and authority of institutional entities for illicit purposes. Such deceptive practices pose significant risks to citizens, businesses, and the government itself. This project addresses the crucial problem of online security and reliability by developing a comprehensive system for identifying fake URLs. It involves data preprocessing, feature engineering, and the utilization of machine learning algorithms, including Random Forest, Decision Tree, and K-Nearest Neighbors, to identify fraudulent URLs. The project seamlessly integrates a user-friendly front end for text-based URL input and a back end for extracting URL features as well as classifying the extracted URL into legitimate or fraudulent.To enhance the system’s robustness, we added a second layer of authentication that uses extracted URL parameters from an SSL certificate .The front end provides real-time predictions from both methods and offers valuable insights into URL characteristics, enabling users to make informed decisions about the authenticity and potential risks associated with web resources. This project serves as a practical solution to enhance online security and user awareness by effectively identifying fake URLs.
