Smart protection for website using machine learning and image processing

Abstract

The internet has become a basic and one of the most important tools for regular life. This ascent in the boundless utilization of innovation carried with it an ascent in various problems. There have been so many loops and data breaches in web content as a result it's become very easy for the criminals to manipulate those security gaps and inject viruses or other unwanted and harmful contents. Almost every one of us faces the problem of getting trapped in malicious sites or clicking on some popped up advertisements which ended up into absolutely an indecent web page that contain potential threats. As a result, most of our private data is being compromised or got leaked, which create so many problems in both our corporate and private life. So, it's become a top priority to the security analyst and consults to ensure web security as it has become an integral part of every sphere. Keeping these facts in our mind, we have come up with an idea of a smart protection concept for web sites that we browse regularly in everyday life. Our aim is to build a model that will prevent us from accessing various malicious sites, unwanted link redirection, and pornographic image contents that pop up quite frequently in the time of browsing webpages. To make our system able to detect these problems, we will implement machine learning and image processing algorithms and provide the users a ltered, smooth, and safe user experience.

Description

Cataloged from PDF version of thesis.
Includes bibliographical references (pages 54-56).
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020.

Keywords

Malicious sites, Machine learning, Link redirection, Image processing, Convolutional neural networks, Web contents, CNN, Web security, Cybersecurity

Citation

Endorsement

Review

Supplemented By

Referenced By