akash1118 / phishing_detector Goto Github PK
View Code? Open in Web Editor NEWThis project forked from arvind-rs/phishing_detector
Chrome extension to detect phishing attempts using Machine Learning
This project forked from arvind-rs/phishing_detector
Chrome extension to detect phishing attempts using Machine Learning
The Phishing Detection Chrome Extension aims to classify, every browsed URL, under phished and non-phished category(on page load); thereby, alerting the user of any malicious activity and prevent intrusion. Steps to install the chrome extension: 1. Google Chrome -> More Tools -> Extensions 2. Click 'Load unpacked extension..' 3. Open the 'Engineering Module' directory 4. Phishing Detection extension ready to monitor all the sites loaded on the Chrome browser Test URLs(positive tests - phishing detected): 1. ../Engineering Module/Phishing.html (Test phished page created) 2. https://www.phishtank.com/phish_search.php?verified=u&active=y (List of phished sites available) ML Algorithms: SVM, Neural Networks and Random Forest algorithms have been used to evaluate the data-set; and the SVM trained persistent model has been passed to the engineering module for phishing detection. Engineering Modules: 1. manifest.json: It provides Chrome with the basic information about the extension like name, permissions, associated scripts and files. 2. content.js: It runs in separate unprivileged javscript environment and has complete access to the DOM. Here, the trained SVM model(weights calculated in ./ML Algorithm Evaluation/run_algorithms.py) has been used as a persistent model to classify websites. Below functions compute feature vector for the portal under analysis: isIPInURL() isLongURL() isTinyURL() isAlphaNumericURL() isRedirectingURL() isHypenURL() isMultiDomainURL() isFaviconDomainUnidentical() isIllegalHttpsURL() isImgFromDifferentDomain() isAnchorFromDifferentDomain() isScLnkFromDifferentDomain() isFormActionInvalid() isMailToAvailable() isStatusBarTampered() isIframePresent() The evaluated feature vector, further, passed to predict(data) function reckons the prediction for the website. 3. background.js: In case, we need access to external extensions or APIs, it is a requisite to create means of communication between the content.js and privileged parts of the our extension, and this interaction is termed as message passing. Message passing allows different components of our extension to collabrate. NOTE: The extension validates every URL call, i.e. in case of URL redirection, it will assess every intermittent URL hit as well.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.