1. An intelligent intruder framework for cyber-attacks using machine learning techniques.
- Author
-
Sarla, Pushpalatha, Jamalpur, Bhavana, and Chandhar, K.
- Subjects
- *
DENIAL of service attacks , *MACHINE learning , *INTERNET protocol address , *RANDOM forest algorithms , *COMPUTER network security - Abstract
Attacks like Distributed Denial of Service (DDoS) pose a major threat to the network's security. Many different firms' servers have fallen prey to such unusual types of attacks. These attacks from the many bots under the direction of the botmaster (cracker) can possibly result in the victim's computational and communication capabilities being severely impaired. To create an effective NIDS, the researchers used datasets that were made accessible to the public. Existing studies' datasets, however, are insufficient since they exclude the most commonly used protocols, such as DHCP, which is essential to network architecture. In a network, IP addresses and other crucial network setup settings are dynamically assigned via the Dynamic Host Configuration Protocol (DHCP). Two research inquiries serve as the foundation for this work: 1) what algorithm will get the best results for identifying Distributed Denial of Service attacks? 2) How accurate would these algorithms be if they were trained on real-world data? We exceeded 96% accuracy with the Random Forest Classifier, and we confirmed our findings using two measures. The results were also compared to other works to ensure that they were adequate. We also provide a thorough study to back up our conclusions. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF