DETECTING PHISHING WEBSITE MACHINE LEARNING

1.1 Introduction

Phishing attack is a simplest way to obtain sensitive information from innocent users. The aim of the phishers is to acquire critical information like username, password and bank account details. Cyber security persons are now looking for trustworthy and steady detection techniques for phishing websites detection. Phishing becomes a main area of concern for security researchers because it is not difficult to create the fake website which looks so close to legitimate website. Experts can identify fake websites but not all the users can identify the fake website and such users become the victim of phishing attack. Phishing attacks are becoming successful because lack of user awareness. Since phishing attack exploits the weaknesses found in users, it is very difficult to mitigate them but it is very important to enhance phishing detection techniques.

As a prelude to other parts of this study, this chapter will discuss the background upon which this study was initiated, the statement of problems that led to this study, the Aim and Objectives of the study. Others are Significance of the study, Scope of work, Limitations of the Study and Definition of technical terms.

1.2 Background of Study

Phishing may be a style of broad extortion that happens once a pernicious web site act sort of a real one memory that the last word objective to accumulate unstable info, as an example, passwords, account focal points, or MasterCard numbers. all the same, the means that there square measure some of contrary to phishing programming and techniques for recognizing potential phishing tries in messages and characteristic phishing substance on locales, phishes think about new and crossbreed procedures to bypass the open programming and frameworks. Phishing may be a fraud framework that uses a mixture of social designing what is additional, advancement to sensitive and personal data, as an example, passwords associate degree open-end credit unpretentious elements by presumptuous the highlights of a reliable individual or business in electronic correspondence. Phishing makes use of parody messages that square measure created to seem substantial and instructed to start out from true blue sources like money connected institutions, online business goals, e.t.c., to draw in customers to go to phony destinations through joins gave within the phishing email.

The general method to detect phishing websites by updating blacklisted URLs, Internet Protocol (IP) to the antivirus database which is also known as “blacklist" method. To evade blacklists attackers uses creative techniques to fool users by modifying the URL to appear legitimate via obfuscation and many other simple techniques including: fast-flux, in which proxies are automatically generated to host the web-page; algorithmic generation of new URLs; etc. Major drawback of this method is that, it cannot detect zero-hour phishing attack.

Heuristic based detection which includes characteristics that are found to exist in phishing attacks in reality and can detect zero-hour phishing attack, but the characteristics are not guaranteed to always exist in such attacks and false positive rate in detection is very high (Mahmoud, 2013). To overcome the drawbacks of blacklist and heuristics based method, many security researchers now focused on machine learning techniques. Machine learning technology consists of a many algorithms which requires past data to make a decision or prediction on future data. Using this technique, algorithm will analyze various blacklisted and legitimate URLs and their features to accurately detect the phishing websites including zero- hour phishing websites.

Metrics accustomed live the visual similarity square measure layout similarity, block-level similarity, and overall vogue similarity. Webpage segmentation forms the bottom to outline these metrics. Salient blocks from the structure of a webpage and also the weighted average of the similarities between the paired blocks is understood as block-level similarity whereas the magnitude relation between the entire no of blocks and weighted variety of matched blocks is understood as layout similarity. The bar graph of the fashion feature helps in scheming the general style similarity i.e. The normalized correlation of the histograms of 2 web pages. The potential phishing pages square measure compared against the particular pages to assess the visual similarities between them within the metrics of the key region, overall vogue, and page layouts. The objective of this research to notice malicious websites, the internet sites square measure chiefly created to urge the info from the user. To notice this sort of web site may be a crucial job. During this paper to notice this sort of internet sites using machine learning and deep learning techniques by victimization this sort of methodologies detection of malicious websites is a simple task.

1.3 Statement of Problem

Investigation reveals the problem of the existing system which entails that; Phishing attacks are becoming successful because lack of user awareness. Since phishing attack exploits the weaknesses found in users, it is very difficult to mitigate them but it is very important to enhance phishing detection techniques. The general method to detect phishing websites by updating blacklisted URLs, Internet Protocol (IP) to the antivirus database which is also known as “blacklist" method.

1.4 Aim and Objectives of the Study

The aim of the study is to design and implement a software that Detect Phishing Website Machine Learning. In achieving this aim, the following specific objectives were laid out as follows to develop an application software that will:

1. Provide information about the current website phishing threats
2. Evade blacklists attackers uses creative techniques to fool users by modifying the URL to appear legitimate via obfuscation and many other simple techniques
3. Detect Uniform Resource Locator (URL) with phishing tools such as; website forms and email address prompts

1.5 Significance of Study

The study will provide information about phishing attacks/threat towards website users which will be relevant to the Financial Institutions and Students. This study will be of immense benefit to other researchers who intend to know more on this study and can also be used by non-researchers to build more on their research work. This study contributes to knowledge and could serve as a guide for other study.

1.6 Scope of Study

The study focuses on the Detection of Phishing Website using Machine Learning application software.

1.7 Limitations of the Study

During the course of this study, many things militated against its completion, some of which are:

1. Time Constraint: The time frame given to accomplish this project was very short due to school academic calendar and it was carried out under pressure which made the researcher not to implement some necessary features.
2. Research material: availability of research material is a major setback to the scope of the study.
3. Frequent power failure: This made the researcher append more money on fuel to ensure sustainable power.
4. Financial Constraint: Insufficient fund tends to impede the efficiency of the researcher in sourcing for the relevant materials, literature or information and in the process of data collection (internet).

1.8 Definition of Terms

Automation: This is the use of automation equipment machines to do work that are previously done by people mainly.

Advent: This has to do with the arrival or approach of an important person, event.

Computer: This is an electronic device that accepts, process and sores the processed data as information that may be use for another operator.

Constraints: This is defined as a thing that limits or restricts an individual from processing.

Database: It is a large stores data held in a computer and accessible to a person e.g. individual same, address, sex etc.

Computer hardware: This are those physical peripheries that one can see touch in a computer system and also medical attach to the computer to examine patience body.

Computer software: These are program store in the computer by the manufactures. And more programs can also be stores by the manufactures. And more programs can also be store by the person that bought the computer to be specific task.

Insufficient material: Since the hospital have not introduced the using the computer in previous years. It is very difficult to get necessary material needed to carry out this study and material that are related to online medical system.

Hard copy: Is the information that is displayed on the screen.

Medical laboratory: This is a place where patient are tested, examined to know the particular problem that they have before treatment.

Website: This is defined as the network of web pages that contain information about a person organization.