Web Application Attack Pattern Extraction using Deep Learning

Please enable javascript in your browser.

Rezvani, Mostafa | 2020

309 Viewed

Type of Document: M.Sc. Thesis
Language: English
Document No: 53346 (52)
University: Sharif University of Technology, International Campus, Kish Island
Department: Science and Engineering
Advisor(s): Jalili, Rasool
Abstract:
One of the most important requirements in deploying a security system is to ensure the effectiveness and absence of bypass patterns. This is especially important for attack-based detection systems. One of the systems that has recently attracted the attention of network administrators is Web Application Firewall (WAF). The purpose of this thesis is to propose a deep learning approach to identify the pattern of SQL Injection (SQLi) attacks which could potentially bypass a WAF. We delve into the problem of detecting SQLi attacks among a very large dataset of existing SQL queries. To this end, we use one of the latest implementation of Recurrent Neural Network (RNN) called Long Short-Term Memory (LSTM). The algorithm is fed with a dataset of blocked and bypassed SQLi queries. We implemented a Pytorch based program for the model and finally evaluated the accuracy, time consumption and number of successfully detected attacks. The results are satisfactory compared to the surveyed related literature
Keywords:
Deep Learning ; Machine Learning ; Web Application ; Web Attack ; Firewall System ; Web Applications Firewall (WAF)

No TOC