Web-Based Threat Identification Using Classification Algorithm

The word “malware” refers to an intent to harm. In order to harm the end user, a malware website spreads malware, infects the victim's system, and steals important information. In the year 2020, the global lockdown saw an increase in and shift toward using internet services as a mode of operation while staying at home. This, in turn, led to an increase in the number of cybercrimes committed by criminals and significant data breaches suffered by businesses. To stop these attacks, malware URLs and threat types must be located. Static properties that describe these behaviors can be used to identify most malware web pages because they import exploits from distant resources and conceal exploit code. To identify such phishing URLs, several models and methods have been proposed in recent years (Dawoud and Shahristani in Internet Things 3:82–89, 2018). The previous research is reviewed and a machine learning strategy for the most accurate detection of malware websites using a machine learning model is proposed in this paper. In addition, we conduct a reconnaissance on the URL to provide additional information regarding whether the URL is good or malware or phishing. In summary, this study aids in the advancement of a web-based system for recognizing threats, leading to the proactive identification and resolution of dangers in realtime. The system has the capability to be incorporated into current security structures, offering an extra level of protection against attacks occurring on the internet and ensuring the preservation of online users’ privacy and integrity.