Leveraging blockchain and machine learning to counter DDoS attacks over IoT network

The paper presents an approach for detecting Distributed Denial of Service (DDoS) attacks using machine learning and blockchain technology. With the increasing complexity and frequency of DDoS attacks, network security faces significant challenges. The proposed approach aims to detect DDoS attacks in a real-time environment by applying machine learning algorithms and storing false IP addresses in a blockchain ledger. The decentralized nature of the blockchain network makes it extremely difficult for attackers to tamper with the stored information. By utilizing blockchain to store blacklisted IP addresses and their timestamps, the approach ensures the integrity and correctness of the data. The performance of the proposed approach is evaluated on a combination of CSE-CIC-IDS2018-AWS, CICIDS2017, and CICDoS2016 datasets, demonstrating its effectiveness. The Random Forest model outperforms other models by achieving 99.34% accuracy, indicating that the proposed method accurately identifies DDoS attacks in real-time and securely stores the false IP addresses in a transparent blockchain ledger.