Detection of Application Layer DDOS-Attacks Produced by Various Freely Accessible Toolkits Using Machine Learning

The project aims to detect and mitigate escalating application-layer DDoS attacks, providing insights into attack patterns and tools for enhanced cybersecurity measures. With a target on HTTP-layer attacks, the project seeks to unravel tactics and tools, offering a specialized approach to bolster understanding and countermeasures against evolving cyber threats. There is an urgent need to address rising DDoS threats by shifting the project focus to tools' accessibility. This is crucial for proactive defense against the widespread use of malicious attack tools. The project aims to empower network administrators and cybersecurity experts, securing online services. Ultimately, it benefits users and businesses with resilient defenses against evolving DDoS threats. To boost performance, we introduced ensemble models—Voting Classifier (RandomForest, DecisionTree) and Stacking Classifier (RandomForest, DecisionTree, LGBM). These enhancements aim to improve cyberbullying detection accuracy.. Key Words: DDoS, DDoS tools, machine learning, deep learning