• Khalid Shaikh
• Supriya Shelar
• Abhishek Prasad

Phishing is a massive threat to all Internet users, and it's difficult to track down or protect against because it doesn't seem to be malicious. In today's world, everything is uploaded to the internet, putting personal information at risk. Phishing affects people all over the world and is carried out on a large scale, making it impossible to track down and prosecute the perpetrators. Just one common technique that phishers have used is a tactic known as "quick flux," in which they use a wide pool of proxies and URLs to hide the true location of the phishing site. This makes it more difficult to blacklist the site, and it takes longer to locate the server. Through blacklisting or banning phishing pages, or filtering out phishing emails, phishing can be stopped before it hits the user. The first approach involves manually inspecting URLs and the places that they claim to be, or using machine learning to automate the process. Owing to the more nuanced nature of phishing, there are few effective spam filters used by email servers. Machine learning techniques are now being used to create phishing filters. ‘‘Modeling and Preventing Phishing Attacks': The author of this paper has included a set of visual aids to help readers understand how phishing attacks function. The authors also clarify how each of these variables is interpreted. In their paper, "Classification of Phishing Email Using Random Forest Machine Learning Technique," the authors describe the characteristics used to identify phishing emails. Using URLs with an IP address, non-matching 'href' attributes and connection text, the number of dots in a domain name, and testing domain names against the email sender are a few examples. Their experiment yielded an accuracy of 99.7 percent with a very low false positive rate of about 0.06 percent. There is a comparison study of anti-phishing detection, prevention, and security mechanisms from the previous decade. On the basis of email structure, the vulnerable area is divided into three groups. The number of vulnerabilities protected by current anti-phishing mechanisms is identified in order to determine if the vulnerability is centered or unfocused. This research paper can be thought of as a tutorial for a decade's worth of anti-phishing research. The current study investigates the efficacy of methods and strategies used to combat email phishing.

Phishing detection system, Malicious URL, Email spam, Anti-phishing, Cyber Threat.

"Phishing Detection: Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 11, page no.b452-b459, November-2021, Available :http://www.jetir.org/papers/JETIR2111157.pdf

"Phishing Detection: Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 11, page no. ppb452-b459, November-2021, Available at : http://www.jetir.org/papers/JETIR2111157.pdf