Unifying Assurance A Framework for Ensuring Cloud Compliance in AIML Deployment
Samir Vinayak Bayani, Sanjeev Prakash, Jesu Narkarunai Arasu Malaiyappan
Abstract
Intrusion poses a significant challenge in Cloud networks, necessitating the development of efficient mechanisms to mitigate intrusions and enhance system security. To address this, we propose a novel Artificial Bee-based Elman Neural Security Framework (ABENSF). This framework involves rescaling the raw dataset using preprocessing functions and integrating an optimal fitness function based on artificial bees into the feature extraction phase to identify and extract attack features. Additionally, the monitoring mechanism in ABENSF enhances network security by proactively preventing attacks. By employing tracking and monitoring functions, known and unknown attacks can be effectively thwarted. We validate the proposed framework using the NSL-KDD dataset in Python software and conduct a comparative analysis to assess its performance against existing techniques. Our results demonstrate that the developed model outperforms other methods in terms of attack prevention and overall security enhancement.