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

Suganya and Sasipraba Journal of Cloud Computing (2023) 12:74 https://doi.org/10.1186/s13677-023-00442-6 Journal of Cloud Computing: Advances, Systems and Applications Open Access RESEARCH Stochastic Gradient Descent long short‑term memory based secure encryption algorithm for cloud data storage and retrieval in cloud computing environment M. Suganya1* and T. Sasipraba2 Abstract 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 shortterm 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. Keywords Spatial data, Cloud computing, Cryptosystem, Cipher texts, Multi authority, Data correctness *Correspondence: M. Suganya 1 Research Scholar, Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, Tamil Nadu, India 2 Vice Chancellor, Sathyabama Institute of Science and Technology, Chennai, Tamil Nadu, India Introduction To a new computer paradigm known as cloud computing, many services are available on demand and at a minimal cost. Cloud computing’s main objective is to offer quick, simple data and compute data storage. Cloud computing and other contemporary computer designs provide a wide range of immediately available properties. The main idea of cloud computing is to offer specific, quick functions for data processing and storing in a cloud architecture [1]. The computing industry is adept at controlling the dangers and hazards that the environment of © The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Suganya and Sasipraba Journal of Cloud Computing (2023) 12:74 cloud computing poses. One method for improving cloud computing security is to use cryptography, which is the main element of cloud security. Furthermore, it is a technique for converting the user’s letter into a cipher text, a coded phrase only the intended receiver can decipher and expose the concealed message. Secrecy is achieved throughout the transmission of data or communications. A mathematical method for handling authentication, such as encryption, and data integrity, is known as cryptology. It is conceivable to provide these security services since cryptography offers a variety of reliable possibilities [2]. Private data signified by cryptography (Hybrid Algorithms, Symmetric Methods, and Asymmetric Algorithms) is encrypted and decrypted using encryption protocols, digital signatures, and hashing algorithms of numerous well-known encryption algorithms [3]. For each of these current techniques, there are security issues. These techniques also take a long time to generate cryptographic keys, retrieve keys, encrypt data, and decrypt data. A new cloud computing paradigm integrates high-level IT services alongside low-level resources abstractly. As a result, the user can quickly access numerous applications using an abstract cloud. The cloud-based outsourcing information storage and delivery service is one of the most likely uses. Some examples of these cloud storage services are Azure from Microsoft, Simple Storage Service, and CDNs like Cloud Front from Amazon Web Services. A third-party information center, a provider of cloud-based services, serves a significant role as an information management entity in a cloud storage system (CSP). The CSP can investigate data items kept in cloud storage without the consent of the data owners because it is the authority controlling the data items stored in the system. Unfortunately, most commercial cloud storage systems we are aware of offer essential storage services with plaintext data content storage. Even when the data owners do not want to disclose anything, there is a privacy issue involving the outsourced data due to either the CSP’s malfunction or abuse for illegal profit. Some sensitive information, including medical records, financial graphs, or company reports, should be protected against exposure to unauthorized parties, according to the perspective of the data owners. As a result, the literature is paying more attention to the security and privacy concerns with this CSP and the potential illicit users. In other words, additional mechanisms like cryptographic methods are required, and data access management should be included in the hands of the CSP. By using cryptographic techniques, the information owner can encrypt the content of their data before outsourcing rather than leaving it in plaintext. The CSP (...truncated)