click here to download project abstract
Abstract:
The Internet has become an indispensable part of our life, However, It
also has provided opportunities to anonymously perform malicious activities
like Phishing. Phishers try to deceive their victims by social engineering or
creating mockup websites to steal information such as account ID, username,
password from individuals and organizations. Although many methods have
been proposed to detect phishing websites, Phishers have evolved their methods
to escape from these detection methods. One of the most successful methods for
detecting these malicious activities is Machine Learning. This is because most
Phishing attacks have some common characteristics which can be identified by
machine learning methods. In this paper, we compared the results of multiple
machine learning methods for predicting phishing websites.
2. Existing System:
Existing CTI for phishing website detection methods can be
divided into three types: lookup systems, fraud cuebased methods, and deep
representation-based methods. The lookup system detects a phishing website by
―looking up‖ the website URL against a blacklist of phishing URLs and an
alarm is raised when the website‘s URL appears in the list. The blacklists are
classifiers (e.g., SVM, decision tree) and novel machine learning methods (e.g.,
statistical learning theory based methods, genre tree kernel methods and
recursive trust labeling algorithm) have been devised to detect phishing
websites. Similarly, website traffic based fraud cues requires to analyze the
website traffic within a period of time, making them hard to meet the real-time
detection requirement.
2.1 Disadvantages:
1. It takes more time to make the transfer learning if we want to change some
features and train the model.
2. They are not mentioning the Accuracy of the model.
3. The performance metrics like recall F1 score and comparison of machine
learning algorithm is not done.
4. The performance is not good and its get complicated for other networks.
