A Distributed Deep Learning System for Web Attack Detection on Edge Devices

Abstract: Today’s world is a digital world, where decisions are taken on the internet and the internet forms a very integral and important part of the society and the economy. Naturally, the internet’s security, essentially the security of the World Wide Web (www) is very important and groundbreaking. The internet is often vulnerable to attacks from possible hackers who try to compromise the system in order to illegally poach the resources of the system under question. These attacks are famously called web attacks and are a very common problem amongst the computer fraternity. Though there are several existing systems to counter the problem of attacks on the web, most of these systems have their own drawbacks, as in they do not provide classification on any other grounds except frequency, thus causing many web attacking http requests to fall out of the bracket. The objective of our project is to detect these web attacks from the http requests based on many parameters, and classify them as web attacks or not. We also plan to further classify the attacks as HTML, JavaScript or SQL attacks, thus providing a novelty. Thus, the system solves the problem of undetected web attacks through http requests and thus increases the security of the system manifold.

Keywords: Supply World Wide Web (www), web attacks, web attacking http requests, HTML, JavaScript or SQL attacks.