Cross-Site Scripting (XSS) is one of the most prominent types of web application assaults. It is one of the most serious hazards to online applications and one of the top vulnerabilities, according to the Open Web Application Security Project (OWASP). As a result, detecting and countering this attack is crucial. As a result, we've demonstrated how to leverage the LSTM (Long Short Term Memory) model to detect the XSS Attack Script in this paper. First, we acquired several scripts for the dataset from the XSS vulnerability archives, and then we pre-processed the data by generalizing it, tokenizing it, and changing text to the sequence. The processed data then is trained and tested using the LSTM Model, a Recurrent Neural Network. With a precision rate of 99.57 percent and an f1 score of 99.78 percent, the proposed approach can yield a substantial outcome.

The paper got accepted in Springer Advances in Intelligent Systems and Computing (ICICC 2022)

Authors: Ishan Joshi, Harsh Kiratsata (BISAG-N)

Guide: Punit Lalwani (BISAG-N), Co-Guide: Harsh Kiratsata (BISAG-N)