Biblio

In today's smart healthcare system, medical records of patients are exposed to a large number of users for various purposes, from monitoring the patients' health to data analysis. Preserving the privacy of a patient has become an important and challenging issue. outsourced Ciphertext-Policy Attribute-Based Encryption (CP-ABE) provides a solution for the data sharing and privacy preservation problem in the healthcare system in fog environment. However, the high computational cost in case of frequent attribute updates renders it infeasible for providing access control in healthcare systems. In this paper, we propose an efficient method to overcome the frequent attribute update problem of outsourced CP-ABE. In our proposed approach, we generate two keys for each user (a static key and a dynamic key) based on the constant and changing attributes of the users. Therefore, in case of an attribute change for a user, only the dynamic key is updated. Also, the key update is done at the fog nodes without compromising the security of the system. Thus, both the communication and the computational overhead associated with the key update in the outsourced CP-ABE scheme are reduced, making it an ideal solution for data access control in healthcare systems. The efficacy of our proposed approach is shown through theoretical analysis and experimentation.

Enforcing security and resilience in a cloud platform is an essential but challenging problem due to the presence of a large number of heterogeneous applications running on shared resources. A security analysis system that can detect threats or malware must exist inside the cloud infrastructure. Much research has been done on machine learning-driven malware analysis, but it is limited in computational complexity and detection accuracy. To overcome these drawbacks, we proposed a new malware detection system based on the concept of clustering and trend micro locality sensitive hashing (TLSH). We used Cuckoo sandbox, which provides dynamic analysis reports of files by executing them in an isolated environment. We used a novel feature extraction algorithm to extract essential features from the malware reports obtained from the Cuckoo sandbox. Further, the most important features are selected using principal component analysis (PCA), random forest, and Chi-square feature selection methods. Subsequently, the experimental results are obtained for clustering and non-clustering approaches on three classifiers, including Decision Tree, Random Forest, and Logistic Regression. The model performance shows better classification accuracy and false positive rate (FPR) as compared to the state-of-the-art works and non-clustering approach at significantly lesser computation cost.