Loading

Mitigating DDoS Attacks in Virtual Machine Migration: An In-Depth Security Framework Utilizing Deep Learning and Advanced Encryption Techniques
Venkata Subramanian N.1, Shankar Sriram V S.2

1Dr. Venkata Subramanian N., School of Computing, SASTRA Deemed-to-be University, Thanjavur (Tamil Nadu), India.

2Dr. Shankar Sriram V S., Center for Information Super Highway (CISH), School of Computing, SASTRA Deemed-to-be University, Thanjavur (Tamil Nadu), India.  

Manuscript received on 27 December 2024 | First Revised Manuscript received on 02 January 2025 | Second Revised Manuscript received on 07 January 2025 | Manuscript Accepted on 15 January 2025 | Manuscript published on 30 January 2025 | PP: 12-20 | Volume-14 Issue-2, January 2025 | Retrieval Number: 100.1/ijitee.B103214020125 | DOI: 10.35940/ijitee.B1032.14020125

Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | SSRN | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Safeguarding virtual machines (VMs) during migration is essential to avert Service Level Agreement (SLA) violations. This research article presents a robust security framework that utilizes deep learning and advanced encryption methods to reduce the impact of Distributed Denial of Service (DDoS) attacks during virtual machine migration. The study introduces an Improved Sparrow Search Algorithm-based Deep Neural Network (ISSA-DNN) for the classification of DDoS attacks and utilizes Advanced Encryption Standard-Elliptic Curve Cryptography (AES-ECC) to safeguard virtual machine images. The primary objective is to mitigate the risks associated with VM migration by identifying DDoS attacks and safeguarding VMs using advanced cryptographic techniques. The research employs the Canadian Institute for Cybersecurity Distributed Denial of Service (CICDDoS) dataset, implementing preprocessing procedures like duplication elimination, feature selection via Random Forest, and normalization to improve the precision of the DNN classifier. The ISSA-DNN approach enhances hyperparameter optimization by inverse mutation-based sparrow search, yielding a precise attack classification model. Furthermore, the research incorporates AES-ECC for encrypting VM images, amalgamating AES’s computational efficiency with ECC’s improved security. In contrast to conventional methods, this hybrid encryption approach enhances throughput and decreases encryption and decryption durations, rendering it appropriate for high-throughput and real-time applications. Experimental findings indicate that the proposed ISSA-DNN attains a classification accuracy of 98.79%, surpassing current state-of-the-art techniques. The AES-ECC encryption technique markedly enhances performance metrics, safeguarding the security of virtual machines during migration. This proactive security policy safeguards sensitive data and guarantees adherence to regulatory standards. In conclusion, the established framework offers a comprehensive solution for mitigating DDoS attacks and safeguarding VM migration via advanced deep learning and encryption methodologies. Integrating ISSA-DNN for attack classification and AES-ECC for encryption offers a robust strategy for improving cybersecurity in cloud environments.

Keywords: AES-ECC Hybrid Encryption, Cloud Infrastructure Security, Deep Neural Network (DNN) for Cybersecurity, Distributed Denial of Service (DDoS) Attack Detection, Random Forest Feature Selection, Virtual Machine (VM) Migration Security.
Scope of the Article: Computer Science and Applications