Enhanced cloud security via optimal fire hawks XOR and probabilistic super learning

Every visit to a doctor leaves a record of diagnoses, prescriptions and test results, and patients rely on those records staying safe for years to come. Despite its widespread use and vast range of services, cloud computing presents privacy and security concerns, thus international organizations are developing cloud security policies and procedures. Given its effective data security and reliability methods, AI technology is widely applied in healthcare. This research proposes an AI-based effective feature learning model using Probabilistic Super Learning (PSL) and OFHXOR encryption. The OFHXOR’s Fire Hawks Optimizer (FHO) selects the best key value to encrypt healthcare data. Probabilistic Super Learning is used to detect malicious attacks. While updating the learning model, the PSL controls the reported attack’s attributes and properties. To evaluate the effectiveness of the proposed model of cloud security, the experiments were conducted on the WUSTL-EHMS-2020 and ECU-IoHT datasets to assess intrusion detection. The encryption and decryption performance of the OFHXOR module is evaluated on the patient biometric records of the WUSTL-EHMS-2020 dataset, serialized into payloads of 10–50 MB. Quantitative results obtained from the experiments indicate the effectiveness of the proposed model of cloud security in detecting the presence of attacks with a detection accuracy of 95.68%, a security level of 98.56%, and a low level of attacks of 4%. Moreover, the model obtained a precision of 94.51%, a recall of 93.96%, and a Matthews Correlation Coefficient (MCC) of 95.71%, which are higher than the ANN, KNN and SVM baselines, while the security level exceeds that of the RSA and ECC schemes.