Details

Autor(en) / Beteiligte

• Suganya, M.
• Sasipraba, T.

Titel

Stochastic Gradient Descent long short-term memory based secure encryption algorithm for cloud data storage and retrieval in cloud computing environment

Ist Teil von

• Journal of cloud computing : advances, systems and applications, 2023-12, Vol.12 (1), p.74-17, Article 74

Ort / Verlag

Berlin/Heidelberg: Springer Berlin Heidelberg

Erscheinungsjahr

2023

Link zum Volltext

Quelle

EZB Electronic Journals Library

Beschreibungen/Notizen

• With the increasing rise of distributed system technologies, one of the most pressing problems facing the digital world is ensuring the security of sensitive and confidential data during transport and storage, which is also regarded as one of the most critical difficulties facing cloud computing. Numerous techniques exist for enhancing data security in the cloud computing storage environment. Encryption is the most important method of data protection. Consequently, several accessible encryption strategies are utilized to provide security, integrity, and authorized access by employing modern cryptographic algorithms. Cloud computing is an innovative paradigm widely accepted as a platform for storing and analysing user data. The cloud is accessible via the internet, exposing the data to external and internal threats. Cloud Service Providers (CSPs) must now implement a secure architecture to detect cloud intrusions and safeguard client data from hackers and attackers. This paper combines Stochastic Gradient Descent long short-term memory (SGD-LSTM) and Blow Fish encryption to detect and prevent unauthorized cloud access. User registration, intrusion detection, and intrusion prevention are the three phases of the planned system. The SGD-LSTM classifier predicts cloud data access and prevents unauthorized cloud access. In the data access phase, cloud data access is managed by authenticating the authorized user with the Blowfish encryption algorithm. Comparing the proposed classifier to existing classifiers demonstrates that it detects abnormal access accurately. The experimental outcomes enhanced data security, which can be utilized to protect cloud computing applications. The experimental results of the suggested SGD-LSTM algorithm indicated a high level of protection, as well as a considerable improvement in security and execution speed when compared to algorithms that are often used in cloud computing.