• Aalla Harsha Vardhan Sai
• Dumpala Nikhil Reddy

Phishing attacks have been a constant problem for years, despite diminution efforts from industries and the academic side. There were many attacks caused due to the insecure behavior. We accept that users fall into the trap of these websites because of a lack of education on it and not aware of these security threats and visible virtual environment unusuality on the sites they visited. Users who use smart gadgets and devices tend to fall into this trap even more than computer users due to the screen size and performance. Most of the users fall into a hitch due to opening unnatural links and responding to unfamiliar recipients. Our project will help the users detect these kinds of phishing websites and reduce the risk of falling into this trap, and it can be useful for mobile phone and desktop users. Thus, we implemented a lightweight algorithm for detecting a spamming website without user activity. Our project is working in a real-time environment and is independent of any pre-defined data sets. We used some of the authorization agents and looked into the http responses to determine the authorized webpages. Pop up window will be appeared to check whether the link is malicious or not. Regression and Classification are the main concepts used in our project.

—Classification Techniques, Machine Learning, Spam Detection, Spam Filtering, Count Vectorizer, Cyclic Learn, TFID Vectorizer.

"Malicious Url Prediction Using Machine Learning Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 2, page no.798-802, February-2021, Available :http://www.jetir.org/papers/JETIR2102094.pdf

"Malicious Url Prediction Using Machine Learning Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 2, page no. pp798-802, February-2021, Available at : http://www.jetir.org/papers/JETIR2102094.pdf