Online Bus Ticketing Application

Abstract

The proliferation of web-based applications and
services has led to a significant rise in the
frequency and sophistication of cyberattacks. From
SQL injections to cross-site scripting (XSS) and
denial-of-service (DoS) attacks, these threats can
cause serious disruptions and data breaches. The
need for intelligent, scalable, and accurate detection
systems is more urgent than ever. This project aims
to conduct a comprehensive performance analysis
of various Machine Learning (ML) and Deep
Learning (DL) algorithms to detect web-based
attacks effectively. By leveraging well-established
datasets and evaluation metrics, we assess each
algorithm’s capacity to identify different categories
of web threats. The models explored include both
classical ML algorithms—such as Support Vector
Machines (SVM), Decision Trees, and Random
Forests—and advanced DL models like
Convolutional Neural Networks (CNNs) and Long
Short-Term Memory (LSTM) networks. Each of
these is evaluated under consistent data and
performance metrics.
Through comparative analysis, this research seeks
to recommend the most efficient models for realtime
implementation, balancing performance,
scalability, and interpretability. The insights gained
will contribute to the design of more robust
intrusion detection systems for modern web
infrastructure.