Usage and utility of the World Wide Web has become an integral part of human life in their daily routine for communicating information and disseminating knowledge so rapidly as well as easily in time. Locating theft and cheating are the dual faces of cyber-crime in which hackers and malicious users procure the personal information of the existing genuine users for attaining the illegal financial gain. Malicious URLs host various luring episodes such as phishing, spam, drive-by exploits and so on and thereby hoodwinks the gullible users to become the scapegoat of such scams by suffering pecuniary loss, loss of personal information and malware installation etc., and thereby makes the victims to incur severe loss to the extent of billions of dollars every year. In fact, this sort of fraud has been detected traditionally by using the blacklists, which cannot be exhaustive and also lacking the ability to detect the newly generated notorious and malicious URLs. Hence in order to detect such a heinous crimes, it is the need of the hour to incept a fool-proof system with a wider ramification coupled with its velocity, preciseness to detect the origin and promoter of such malicious contents. The improvised Convolution Neural Network (CNN) model system proposed by the authors is one of such a candid system fettered with re-learning ability Keywords: Cyber Security, TF-IDF Classification, Deep Learning, Neural Network.
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL
₹10000 (INR)
NON IEEE -2021