An Efficient Machine Learning Based Data Auditing Scheme for Cloud Users

With the wide spread of the digital world, IoT devices generate huge amounts of data and store it in cloud servers as they have less storage space. When data is outsourced to the cloud servers, IoT device users lose control of it, which means the confidentiality and integrity of the data can be compromised. Further, several Third-Party Auditors (TPAs) are available to check the integrity of the data. But most of the TPAs are based on trust. In some cases, TPAs are being hired by Cloud data centers and in some cases, the TPAs may have direct connection with data consumers. In both the cases, there is a bias and the data may be at high risk. Therefore, to overcome the trust issue, in this paper an Efficient Machine Learning based Data Auditing Scheme for Cloud Users is proposed using a hybrid recommendation system. A repository is maintained which keeps track of all TPA's history. The user submits auditing request to the repository which will run the recommendation system to select appropriate TPA to check the integrity of the user data in the cloud. It chooses the best TPA and gives the auditing results to the user. The proposed scheme reduces the risk of user data.