Detection of DDOS Attack in Cloud Computing Environment using Artificial Neural Network

One of the most severe threats against cloud systems is Distributed Denial of Service (DDoS) attacks. DDoS attacks create a type of resource crippling by flooding the system with abnormal traffic, hence overwhelming all the resources like memory, CPU, and network bandwidth, bringing the services out of reach to legitimate users. It becomes quite difficult to detect such attacks when the requests originate from hundreds of geographically dispersed sources. As such, we propose an ANN-based DDoS attack detection approach that leans on machine learning to enhance the accuracy and efficiency in detecting attacks. The ANN model is designed to pick out underlying patterns in the network traffic and distinguish between legitimate and malicious activities that might originate from either side, thus reducing false positives and false negatives. A particular advantage of cloud computing is its scalability, through which changing demands can be catered to, but it needs robust security against DDoS attacks in order to maintain the service. This ANN-based approach especially focuses on ethical AI principles and sustainability, while being non-discriminatory in access to services. For it reduces errors to ensure fairness in detection, fine-tuning for energy efficiency also turns out to lead to a smaller ecological footprint.