Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
52,427
result(s) for
"Cloud Security"
Sort by:
Cloud computing
An \"overview of the implications of the cloud phenomenon and the opportunities and risks associated with it\"-- Provided by publisher.
Book
BVFLEMR: an integrated federated learning and blockchain technology for cloud-based medical records recommendation system
Blockchain is the latest boon in the world which handles mainly banking and finance. The blockchain is also used in the healthcare management system for effective maintenance of electronic health and medical records. The technology ensures security, privacy, and immutability. Federated Learning is a revolutionary learning technique in deep learning, which supports learning from the distributed environment. This work proposes a framework by integrating the blockchain and Federated Deep Learning in order to provide a tailored recommendation system. The work focuses on two modules of blockchain-based storage for electronic health records, where the blockchain uses a Hyperledger fabric and is capable of continuously monitoring and tracking the updates in the Electronic Health Records in the cloud server. In the second module, LightGBM and N-Gram models are used in the collaborative learning module to recommend a tailored treatment for the patient’s cloud-based database after analyzing the EHR. The work shows good accuracy. Several metrics like precision, recall, and F1 scores are measured showing its effective utilization in the cloud database security.
Journal Article
I-MPaFS: enhancing EDoS attack detection in cloud computing through a data-driven approach
Cloud computing offers cost-effective IT solutions but is susceptible to security threats, particularly the Economic Denial of Sustainability (EDoS) attack. EDoS exploits cloud elasticity and the pay-per-use billing model, forcing users to incur unnecessary costs. This research introduces the Integrated Model Prediction and Feature Selection (I-MPaFS) framework to address EDoS attacks. I-MPaFS framework enhances an existing dataset to improve performance, using the generated data to build a Random Forest model for EDoS detection. Our investigation employs the UNSW-NB15, CSE-CIC-IDS18 and NSL-KDD datasets, demonstrating the proposed method’s superiority over existing techniques. The model achieved recall scores of 99.45% on the UNSW-NB15 dataset, 98.19% on the CSE-CIC-IDS18 dataset, and 99.82% on the NSL-KDD dataset, highlighting its reliability and efficacy in safeguarding cloud users from financial exploitation. This study contributes to the field by evaluating current EDoS detection methods, introducing the I-MPaFS framework, validating its performance with benchmark datasets, and comparing its effectiveness against state-of-the-art techniques. The findings affirm the significant potential of I-MPaFS in enhancing cloud security and protecting users from EDoS attacks.
Journal Article
Secure Multi-Cloud Storage Systems Techniques for Data Integrity and Availability
Cloud computing is constantly changing, and the provision of efficient and safe data management has led to a prominent challenge in the virtualization age - security for multi-cloud storage systems. This study provides a holistic way to solve the problems of data security and accessibility in multiple cloud environments. The paper identifies scalable and cost-saving solutions, which promise to make sure data are secure from attacks while also being readable across cloud service providers, reducing the problems of vendor lock-in, latency, and expense. As a solution to mitigating the risk of data loss, data tampering, and data availability challenges, this research proposes an innovative framework that lays out protocols for data integrity verification, unauthorized access prevention, and assurance for continuous data availability, built on the foundation of blockchain technology, real-time monitoring systems, and multi-degree redundancy. In addition, the paper presents cost-effective methods such as deduplication, automated failover mechanisms, hybrid cloud storage architecture allow us to build cheaper, lucid and more efficient systems compared to previous systems. The paper provides novel approaches that contribute towards improving the performance, security and reliability of multi-cloud storage systems, thus helping to overcome the major barriers of cloud computing, the third wave of computing on a data intensity basis, with potential implications for data management in future cloud environments.
Journal Article
An enhanced encryption-based security framework in the CPS Cloud
The rapid advancement of computation techniques and cloud computing has led to substantial advancements in Cyber-Physical Systems (CPS), particularly in the field of health care. There are a variety of ways in which CPS is used in healthcare today, including delivering intelligent feedback systems, automatically updating patient data digitally, monitoring patients passively with biosensors, etc. In recent years, cyber-physical systems have become capable of making lifesaving decisions as they are becoming more connected to the cloud. However, healthcare has become one of the most critical issues for many. A CPS network uses the Internet of Medical Things (IoMT) to continuously monitor patients’ health metrics such as body temperature, heart rate, etc. Due to physical connectivity restrictions, networks are more susceptible to security threats. In spite of the fact that the data is stored in the cloud, it is necessary to provide security regardless of device security and network security. Several cyber-security vulnerabilities have been identified in cloud-based healthcare systems in particular. To give patients a reliable healthcare experience, security concerns with CPSs need to be addressed carefully. In this context, this paper proposes a Cross-Breed Blowfish and MD5 (CBM) approach to improve the security of health data in the CPS cloud. The proposed model uses the wireless sensor network, in which data acquired by the network is transmitted via the transmitting node. Using the fuzzified effective trust-based routing protocol (FET-RP), the most efficient path for data travel is selected. The best route is determined using Butter-Ant Optimization (BAO) algorithm. The proposed method conveys data throughput encryption and decryption in a decoded format. The encrypted data is then stored in the cloud database for security reasons. The route finding algorithm is the one which is sending the data from one end to other end. The data is encrypted based on the source and destination. We compare the performance metrics of our recommended technique to those of other existing techniques, such as RSA, Two fish, ICC, and FHEA, in order to ensure that it performs optimally. The values of Cross Breed Blowfish and MD5 and FET-RP with regard to the performance metrics in terms of encryption (60 ms), decryption (55 ms), latency (60 s), throughput (97 mbps), security level (98%), and execution time (57 ms) which outperforms the conventional methods by 10–15%. Also the proposed encryption shows the considerable improvement in the level of security making our model a real world solution.
Journal Article
Detecting hidden communication threats in cloud systems using advanced pattern and threat propagation analysis
Cloud environments enable scalable multi-tenant computing but introduce security risks like covert channels, making their detection and classification essential for maintaining cloud security. Initially, covert channels exploit shared resource dynamics to mimic normal workload behavior, allowing malicious data transmission to go unnoticed by standard security measures. In addition, covert channels embed signals in encrypted or obfuscated traffic through multi-layered encryption and protocol tunneling, creating inherent noise that attackers exploit to sustain covert communication channels quietly. Hence, to tackle theses drawbacks, a Fourier-Warp Entropic Reinforcement Graph Detector is introduced, combining the Fourier-Warp Convolutional IsoForest Graph Detector and Adaptive Entropic Reinforcement Graph Transformer. This integrated system analyzes temporal and spatial workload patterns, detects abnormal timing behaviors, and identifies hidden communications. It then adaptively refines decisions, ensuring reliable distinction between normal workload fluctuations and covert activity, even when communications are encrypted or obfuscated. Thus, the model learns and classifies diverse covert threats with high precision by mapping inter-tenant relationships, delivering robust and adaptive protection for multi-tenant cloud environments. This method improves cloud security by constantly learning and neutralizing covert threats, achieving high accuracy, recall, and low detection errors, while significantly reducing RMSE.
Journal Article