Phish-Shelter: A Novel Anti-Phishing Browser Using Fused Machine Learning

Phish-Shelter: A Novel Anti-Phishing Browser Using Fused Machine Learning

Rizwan Ur Rahman, Lokesh Yadav, Deepak Singh Tomar, Deepak Singh Tomar
Copyright: © 2022 |Pages: 23
DOI: 10.4018/JITR.2022010104
Article PDF Download
Open access articles are freely available for download

Abstract

Phishing attack is a deceitful attempt to steal the confidential data such as credit card information, and account passwords. In this paper, Phish-Shelter, a novel anti-phishing browser is developed, which analyzes the URL and the content of phishing page. Phish-Shelter is based on combined supervised machine learning model.Phish-Shelter browser uses two novel feature set, which are used to determine the web page identity. The proposed feature sets include eight features to evaluate the obfuscation-based rule, and eight features to identify search engine. Further, we have taken eleven features which are used to discover contents, and blacklist based rule. Phish-Shelter exploited matching identity features, which determines the degree of similarity of a URL with the blacklisted URLs. Proposed features are independent from third-party services such as web browser history or search engines result. The experimental results indicate that, there is a significant improvement in detection accuracy using proposed features over traditional features.
Article Preview
Top

Introduction

With the passage of time, the usage of internet is growing both for individual users and for the organizations. It has become an integral part of our day-to-day social and financial activities. Many of the organizations such as Amazon, Paytm and Myntra offer online trading and online sales of services and goods.

With the increase of front end applications to access the information, internet banking creates the necessity to use reliable methods. In the current scenario, the financial crimes are replaced from direct to indirect attacks. For example, a bank’s client could be targeted with a specific trick instead of a robbery (Philippsohn, 2001).

With the increase of the usage of internet, the internet community is much more vulnerable to security attacks. The network security attacks are primarily physical, syntactic, and semantic attacks (Ashton, 2017).

The physical attacks are committed against physical piece of equipment for instance, hard drives, routers, or other electronic devices.

The Syntactic attacks may be grouped under the term malware or malicious software. These attacks may consist of worms, viruses, and Trojan horses. Syntactic attacks, where networks and operating logic are targeted for example web bot attack Trojan and Denial of Service (Rahman et al., 2012).

And finally, Semantic attack is a type of attack, which directly targets the end users instead of physical device and software application. Instead of taking advantage of system vulnerabilities, semantic attacks make use of the way humans interact with computers or interpret messages. Semantic attacks target user-computer interface with the intention of deceive a user into performing an action that will breach a system's information security (Heartfield et al., 2017).

Recently, the most common semantic attack that has been seen is phishing. Phishing is an identity theft which makes use of both social engineering and fake web-site creating methods issued to deceive user to disclose his/her secret and valuable details. Phishing attacks take advantage of user’s inability to differentiate between legitimate company websites and fake websites.

In phishing, a semantic attacker uses an email message which appears to be from a legitimate business, such as a bank . The messages look similar to the official one, and can contain html links which leads to a website that resembles legitimate business website. The attackers offer some service via this html link.

Anti-Phishing Work Group (APWG) that is a non-profit organization functioning to provide anti-phishing education to improve the public understanding of security. China Internet Network Information Center (CNNIC), Anti-phishing Alliance of China (APAC) and private sources across the world (APWG, 2012).

APWG produces and releases reports in quarterly, half yearly and yearly describing the statistics of malware and malicious domains and phishing attacks in different constituencies of the world.

To Detect Phishing Attacks, till date many different methods have been proposed. According to APWG, defense mechanisms used for phishing attacks are divided into three methods:

  • Content Based Technique

  • Heuristic Based Technique

  • Blacklist Based Technique

Content Based technique inspects the similarity between the original and spoofed web pages to identify web spoofing. One of the main content based techniques is CANTINA (Zhang et al., 2007) which is successful in the identification of phishing website but it disable the keyword extraction.

Heuristic based approach uses HTML or URL signature to identify the spoofed web-pages. Number of researches conducted based on this approach. One of the main heuristics approach solutions used is SpoofGuard. It is anti-decision maker traffic in checking URL characteristics of phishing web-pages. It also extracts URL Characteristics of phishing browser plugins.

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 15: 6 Issues (2022): 1 Released, 5 Forthcoming
Volume 14: 4 Issues (2021)
Volume 13: 4 Issues (2020)
Volume 12: 4 Issues (2019)
Volume 11: 4 Issues (2018)
Volume 10: 4 Issues (2017)
Volume 9: 4 Issues (2016)
Volume 8: 4 Issues (2015)
Volume 7: 4 Issues (2014)
Volume 6: 4 Issues (2013)
Volume 5: 4 Issues (2012)
Volume 4: 4 Issues (2011)
Volume 3: 4 Issues (2010)
Volume 2: 4 Issues (2009)
Volume 1: 4 Issues (2008)
View Complete Journal Contents Listing