Authors:
Harikiran Boye

Addresses:
Department of Software Engineering, Visa, Research Blvd, Austin, Texas, United States of America. hboye@visa.com

Abstract:

The paper makes sense to be concerned about data security and privacy as the dominance of the cloud in the data storage and management space begins. This paper presents a study on enhancing the robustness of the cloud by integrating advanced encryption algorithms with robust anomaly detection mechanisms in order to safeguard sensitive data stored in it. With traditional encryption methods, a strong foundation is laid to protect the data. However, due to the ever-evolving sophistication of cyberattacks, which requires more dynamic protection methods, it is important to always look forward to new methods for protecting data from increasingly sophisticated cyberattacks. This paper combines state-of-the-art techniques in encryption, including homomorphic encryption and quantum-resistant algorithms, together with machine learning-based advanced anomaly detection techniques to detect suspicious activities in real time. The framework uses real-time encryption mechanisms during data transmission together with anomaly detection systems that monitor the access and activity logs in real time. These systems use deep learning algorithms such as convolutional neural networks and long short-term memory to detect unusual patterns so they can offer multi-layered security. The frameworks are evaluated using simulations on large datasets of cloud activities. Results show high accuracy in the anomaly detection task with minimal degradation in the need for computational efficiency to scale large cloud environments.

Keywords: Cloud Security; Advanced Encryption; Anomaly Detection; Data Transmission; Secure Storage; Cloud Computing; Information Security; Quantum Computers; Deep Learning.

Received on: 26/02/2024, Revised on: 29/04/2024, Accepted on: 27/06/2024, Published on: 01/09/2024

DOI: 10.69888/FTSCL.2024.000241

FMDB Transactions on Sustainable Computer Letters, 2024 Vol. 2 No. 3, Pages: 153-163

• Views : 305
• Downloads : 11

Download PDF