Scribd Logo
Upload

Welcome to Scribd!

  • 124 views

    Detection of Phishing Website

    Uploaded by

    Om Raut
    This document discusses detecting phishing websites through machine learning. It proposes using a deep learning method to analyze URL strings and detect suspicious websites. The objectives are to better protect user information and design a detection system based on URL analysis. Related work discusses algorithms like random forest and logistic regression that have been used, along with their advantages and disadvantages. The proposed methodology uses a deep learning approach to extract features from URLs and train a model to identify phishing sites.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Detection of Phishing Website

    Uploaded by

    Om Raut
    124 views12 pages
    This document discusses detecting phishing websites through machine learning. It proposes using a deep learning method to analyze URL strings and detect suspicious websites. The objectives are to better protect user information and design a detection system based on URL analysis. Related work discusses algorithms like random forest and logistic regression that have been used, along with their advantages and disadvantages. The proposed methodology uses a deep learning approach to extract features from URLs and train a model to identify phishing sites.

    Original Description:

    Ppt on detection of phishing website

    Original Title

    Detection of Phishing website

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses detecting phishing websites through machine learning. It proposes using a deep learning method to analyze URL strings and detect suspicious websites. The objectives are to better protect user information and design a detection system based on URL analysis. Related work discusses algorithms like random forest and logistic regression that have been used, along with their advantages and disadvantages. The proposed methodology uses a deep learning approach to extract features from URLs and train a model to identify phishing sites.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    124 views12 pages

    Detection of Phishing Website

    Uploaded by

    Om Raut
    This document discusses detecting phishing websites through machine learning. It proposes using a deep learning method to analyze URL strings and detect suspicious websites. The objectives are to better protect user information and design a detection system based on URL analysis. Related work discusses algorithms like random forest and logistic regression that have been used, along with their advantages and disadvantages. The proposed methodology uses a deep learning approach to extract features from URLs and train a model to identify phishing sites.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 12

    Title: Detection of Phishing Website

    Project Guide: Candidate:


    Dr Ankit Kumar Jain Raut Omprakash Jagannath
    32213219
    Introduction:
     Phishing is a type of social engineering attack which is used for stealing
    personal details of an individual. The information includes passwords,
    bank account details ,credit card details. It occurs when an attacker tries
    to or behave like an legitimate provider. The individual is then fooled into
    clicking a malicious websites link, which can lead to the installation of
    malware, the freezing of the system as part of a ransomware attack or the
    revealing of sensitive information.

     The most phishing attacks are carried out by fake emails, containing a
    URL of a fake malicious Website. There are three types of phishing
    attacks. 1)Spear Phishing 2)Clone Phishing 3)Whaling.
    Problem Statement:
     With the Increasement in online transactions, cybercrime has rapidly
    increased and Hackers attempt to trap the end-users through various
    forms such as phishing, SQL injection, malware, man-in-the-middle,
    domain name system tunnelling, ransomware, web trojan, and so on.
    Among all these attacks, phishing is the most reported attack.

     We know that Phishing attack exploits vulnerabilities of human like


    getting trapped by fake URLs and most of the protection protocols
    fails to detect whole phishing attacks.
    Motivation:
     In present scenario, detecting phishing websites are difficult and so we
    are creating a system that will help user to identify phishing without
    any hesitation. In this system Admin can add phishing website URL or
    fake website into system where system could access and scan the
    phishing website and by using algorithm, it will add new suspicious
    keywords to database.

     There are many solution available but the accuracy is low whenever
    new phishing websites comes.

     In the third quarter of 2022, APWG observed 12,70,883 total phishing


    attacks, a new record and the worst quarter for phishing that APWG
    has ever observed.
    Most Targeted Industries,3Q2022

    Social Media Logistics/Shipping Payment eCommerce/Retail Telecom Cryptocurrency

    Financial Institution Webmail Others


    Ransomware Victim Industries,3Q2022

    Manufacturing Business Services Retail & Wholesale Construction Finance


    Health Care Education Legal Services Government Energy/Resources
    Transportation Others
    Objective:
     The Objective of this project is to provide a better solution for
    detection of phishing websites. Overall, the project aims to improve
    the security and privacy of users personal information like
    passwords, bank credentials and many more.

     Protect them from the websites which seems to be malicious and can
    phish the user and to design detection system based on URL.
    Related Work :
    ALGORITHM / THEIR ADVANTAGE THEIR
    TECHNIQUES DISADVANTAGE

    Simple forward and Easy to use and used to It generally fails when
    linear classification classify fake or phishing normal text is replaced by
    technique.[1][3] websites. image.

    Random Forest Model.[1] It can handle the It fails on phishing


    [3] overfitting problem. websites which use
    Captcha.

    Logistic Regression Effective detection Limits in certain factors


    technique.[1][3] like repetition of and
    incapability of features.
    Support Vector Machine More suitable for many Don’t work perfectly
    Technique.[1][3] variables which are when noisy large datasets
    independent in nature. are used.
    Methodology: Deep Learning Method

     Deep Learning is defined as a machine learning technique, where many


    layers of information processing stations are exploited, by classification
    patterns and characteristics, or by learning by representation. In fact, Deep
    Learning is implemented by neural networks.

     However, it has become popular recently, due to three factors: First, there
    is a notable increase in processing capabilities (e.g., video cards, graphical
    processors, etc.); second, by affordable computer hardware; and third, due
    to recent advances and developments in Deep Learning research.

     Our work focuses on the exploration of surface-level features from URLs


    to train a confidence-weighted learning algorithm. The idea is to restrict
    the source of possible features to the character string of the URL and avoid
    having the vulnerability of extracting host-based information
    References:
     Miyamoto, D., Hazeyama, H., & Kadobayashi, Y. (2009). An evaluation of machine
    learning-based methods for detection of phishing sites. In advances in neuro-information
    processing: 15th international conference, ICONIP 2008, auckland, new zealand,
    november 25-28, 2008, revised selected papers, part I 15 (pp. 539-546). Springer berlin
    heidelberg.
     Ali, waleed. "Phishing website detection based on supervised machine learning with
    Odeh, A., Keshta, I., & Abdelfattah, E. (2021, January). Machine learning techniques for
    detection of website phishing: A review for promises and challenges. In 2021 IEEE 11th
    Annual Computing and Communication Workshop and Conference (CCWC) (pp. 0813-
    0818). IEEE.
     Marchal, Samuel, Kalle Saari, Nidhi Singh, and N. Asokan. "Know your phish: Novel
    techniques for detecting phishing sites and their targets." In 2016 IEEE 36th
    International Conference on Distributed Computing Systems (ICDCS), pp. 323-333.
    IEEE, 2016.
     Blum, Aaron, et al. "Lexical feature based phishing URL detection using online
    learning." Proceedings of the 3rd ACM Workshop on Artificial Intelligence and Security.
    2010.
     https://apwg.org/trendsreports/

    You might also like