Privacy-Preserving Outsourced Support Vector Machine Design for Secure Drug Discovery

Aim

           To allow the cloud to securely use multiple drug formula providers’ drug formulas to train Support Vector Machine (SVM) and Naïve Bayes (NB) provided by the analytical model provider.

Abstract

           In this paper, we propose a framework for privacy-preserving outsourced drug discovery in the cloud, which we refer to as POD. Specifically, POD is designed to allow the cloud to securely use multiple drug formula providers’ drug formulas to train Support Vector Machine (SVM) provided by the analytical model provider. In our approach, we design secure computation protocols to allow the cloud server to perform commonly used integer and fraction computations. To securely train the SVM, we design a secure SVM parameter selection protocol to select two SVM parameters and construct a secure sequential minimal optimization protocol to privately refresh both selected SVM parameters. The trained SVM classifier can be used to determine whether a drug chemical compound is active or not in a privacy-preserving way. Lastly, we prove that the proposed POD achieves the goal of SVM training and chemical compound classification without privacy leakage to unauthorized parties, as well as demonstrating its utility and efficiency using three real-world drug datasets.

Existing System

          We use existing datasets of known drug formulas to train the SVM classifier, and the trained SVM classifier can be used for new drug compound visual scanning. Due to the significant investments and high commercial values involved in drug discovery, privacy is an important factor. When a researcher sends some chemical compounds to the cloud for SVM classification, it is important to ensure that the potential new drug compounds will not be leaked to a third-party, such as a competing pharmaceutical corporation.

Problem Definition

           When a researcher sends some chemical compounds to the cloud for SVM classification no security for new Drug Component.

Proposed System

            We propose a Privacy preserving Outsourced Support Vector Machine Design for Secure Drug discovery in the cloud environment, hereafter referred to as POD. Unlike existing drug discovery frameworks, our POD seeks to achieve it efficiently. We are not using three real time datasets to check the efficiency of potential new drug component. Instead of using existing datasets we are using another one data mining algorithm Naïve Bayes(NB).  This two algorithms are used to train the uploaded drug dataset (CSV file). In final we will get trained data and accuracy for that uploaded dataset. Drug tester will check that new drug component. Drug tester doesn’t know the contents of that file; they will get the trained data only. Then they let us know the file was active or not. And finally, admin will approve the drug component.

Advantage

• We minimize the risk of unauthorized disclosure during the SVM and NB training.
• Multiple pharmaceutical corporations won’t reveal the drug components in detail.