• Ansh Vaghela
• Purav Patel
• Panjab Mane

There has been a massive growth in the sheer number of people using the world wide web in the past 15 years. Services ranging from banking to education, from social media to gaming have attracted many people to perform their daily tasks. Due to this, large chunks of information are transferred through the web on a daily basis. Along with all the advancements made there has been a massive rise in cybercriminals who prey on the wealth of information which is available online. They target unsuspecting users for different types of information ranging from private data to bank details or to even steal identity of a legal person to engage in illegitimate activities. It has been a great challenge for the service providers to keep cybercriminals off their users so that their data is secured at any given time. We know that URLs are a gateway to any service a user wants to access and is also the most vulnerable piece of the link which connects the user to the service. Attackers often spoof or provide fake URL’s which leads users to unknowingly provide them with sensitive data. In this paper we have proposed a machine learning system which uses Logistic Regression to identify malicious URLs. This can be useful for users to check if a URL is safe to visit or not.

Machine learning, URL, Logistic regression, feature extraction

"Detection of malicious URLs using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 5, page no.d249-d253, May-2021, Available :http://www.jetir.org/papers/JETIR2105419.pdf

"Detection of malicious URLs using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 5, page no. ppd249-d253, May-2021, Available at : http://www.jetir.org/papers/JETIR2105419.pdf