Next-Gen AI Cybersecurity Simulator with Real-Time Network Intelligence and Threat Visualization

Abstract

Cybercrime has become a major global security concern, encompassing threats such as phishing, malware distribution, botnets, and Denial of Service (DoS) attacks. Among these, DoS attacks are especially disruptive, as they overwhelm target servers with excessive traffic, causing service downtime and preventing legitimate user access. Conventional defense mechanisms like firewalls and antivirus systems often struggle to handle high-volume traffic and evolving attack patterns effectively. To overcome these challenges, this study presents a proactive DoS attack simulation and mitigation framework that combines real-time network traffic monitoring with intelligent filtering techniques. The system incorporates a network packet monitoring mechanism alongside a Big Data processing model using Hadoop MapReduce, enabling efficient handling and analysis of large-scale traffic. Incoming requests are assessed based on their size in relation to server capacity; requests within acceptable limits are processed, while abnormal or oversized requests are flagged as potential attacks and filtered before reaching the server. The framework consists of three key modules: the Server Module for managing authenticated requests, the Network Monitor Module for parallel packet analysis using MapReduce, and the User Simulation Module for generating both normal and malicious traffic scenarios. Experimental results demonstrate accurate detection and filtering of attack traffic while maintaining smooth processing of legitimate requests. Additionally, Hadoop MapReduce enhances scalability and performance, and a monitoring dashboard provides clear visualization of network activity. The system improves server resilience and ensures reliable service availability.