Secure Outsourcing Drug Data Discovery using SVM in Cloud Computing Environment (original) (raw)
Related papers
Secure the Drug Components Using Naïve Bayes and SVM
2021
Abstract: In this paper, we propose a framework to secure drug components in the cloud. Specifically, we design for multiple drug formula providers’ to use the cloud securely. In our approach, the analyzer trains the drug formulas using Support Vector Machine (SVM) and naïve Bayes. To perform integer and fraction computations in the cloud server, we designed secure computation protocols. We securely train the SVM to privately refresh the selected SVM parameters using the two protocols, which are SVM parameter selection protocol and sequential minimal optimization protocol. We train NB based on Bayes theorem with an assumption of independence among predictors. To determine whether a drug compound is active or inactive in a cloud, the trained SVM and NB classifier is used. Lastly, we prove that the proposed framework achieves the goal that facilitate drug manufacturers to securely outsource their formulas without privacy leakage to unauthorized parties in the cloud for storage and for...
A Collaborative Framework for Distributed Privacy-Preserving Support Vector Machine Learning
Journal of Applied Information Science, 2021
Proper now, propose a constitution for security protecting redistributed medicine revelation within the cloud, which we allude to as Unit. In exact, POD is meant to permit the cloud to securely utilize distinctive remedy equation suppliers' remedy recipes to organize help Vector machine (SVM) gave with the aid of the investigative mannequin provider. In our methodology, we configuration relaxed calculation conventions to allow the cloud server to perform typically utilized quantity and section calculations. To safely prepare the SVM, we constitution a protected SVM parameter alternative convention to select two SVM parameters and develop a secure successive insignificant enhancement conference to secretly invigorate both selected SVM parameters [1, 2, 3]. The prepared SVM classifier may also be utilized to come to a decision if a treatment artificial compound is dynamic or now not in a protection saving means. In conclusion, we reveal that the proposed POD accomplishes the objective of SVM making ready and concoction compound grouping without protection spillage to unapproved events, just as showing its utility and productiveness utilising three certifiable medication datasets.
Maximized Privacy-Preserving Outsourcing on Support Vector Clustering
Electronics
Despite its remarkable capability in handling arbitrary cluster shapes, support vector clustering (SVC) suffers from pricey storage of kernel matrix and costly computations. Outsourcing data or function on demand is intuitively expected, yet it raises a great violation of privacy. We propose maximized privacy-preserving outsourcing on SVC (MPPSVC), which, to the best of our knowledge, is the first all-phase outsourceable solution. For privacy-preserving, we exploit the properties of homomorphic encryption and secure two-party computation. To break through the operation limitation, we propose a reformative SVC with elementary operations (RSVC-EO, the core of MPPSVC), in which a series of designs make selective outsourcing phase possible. In the training phase, we develop a dual coordinate descent solver, which avoids interactions before getting the encrypted coefficient vector. In the labeling phase, we design a fresh convex decomposition cluster labeling, by which no iteration is re...
Classifying confidential data using SVM for efficient cloud query processing
TELKOMNIKA Telecommunication Computing Electronics and Control, 2019
Nowadays, organizations are widely using a cloud database engine from the cloud service providers. Privacy still is the main concern for these organizations where every organization is strictly looking forward more secure environment for their own data. Several studies have proposed different types of encryption methods to protect the data over the cloud. However, the daily transactions represented by queries for such databases makes encryption is inefficient solution. Therefore, recent studies presented a mechanism for classifying the data prior to migrate into the cloud. This would reduce the need of encryption which enhances the efficiency. Yet, most of the classification methods used in the literature were based on string-based matching approach. Such approach suffers of the exact match of terms where the partial matching would not be considered. This paper aims to take the advantage of N-gram representation along with Support Vector Machine classification. A real-time data will used in the experiment. After conducting the classification, the Advanced Encryption Standard algorithm will be used to encrypt the confidential data. Results showed that the proposed method outperformed the baseline encryption method. This emphasizes the usefulness of using the machine learning techniques for the process of classifying the data based on confidentiality.
The growth of the cloud computing services and its proliferation in business and academia has triggered enormous opportunities for computation in third-party data management settings. This computing model allows the client to outsource their large computations to cloud data centers, where the cloud server conducts the computation on their behalf. But data privacy and computational integrity are the biggest concern for the client. In this article, the authors attempt to present an algorithm for secure outsourcing of a covariance matrix, which is the basic building block for many automatic classification systems. The algorithm first performs some efficient transformation to protect the privacy and verify the computed result produced by the cloud server. Further, an analytical and experimental analysis shows that the algorithm is simultaneously meeting the design goals of privacy, verifiability and efficiency. Also, found that the proposed algorithm is about 7.8276 times more efficient than the direct implementation.
Cloud infrastructures for in silico drug discovery: economic and practical aspects
BioMed research international, 2013
Cloud computing opens new perspectives for small-medium biotechnology laboratories that need to perform bioinformatics analysis in a flexible and effective way. This seems particularly true for hybrid clouds that couple the scalability offered by generalpurpose public clouds with the greater control and ad hoc customizations supplied by the private ones. A hybrid cloud broker, acting as an intermediary between users and public providers, can support customers in the selection of the most suitable offers, optionally adding the provisioning of dedicated services with higher levels of quality. This paper analyses some economic and practical aspects of exploiting cloud computing in a real research scenario for the in silico drug discovery in terms of requirements, costs, and computational load based on the number of expected users. In particular, our work is aimed at supporting both the researchers and the cloud broker delivering an IaaS cloud infrastructure for biotechnology laboratories exposing different levels of nonfunctional requirements.
An Efficient Outsourced Privacy Preserving Machine Learning Scheme With Public Verifiability
IEEE Access, 2019
Cloud computing has been widely applied in numerous applications for storage and data analytics tasks. However, cloud servers engaged through a third party cannot be fully trusted by multiple data users. Thus, security and privacy concerns become the main obstructions to use machine learning services, especially with multiple data providers. Additionally, some recent outsourcing machine learning schemes have been proposed in order to preserve the privacy of data providers. Yet, these schemes cannot satisfy the property of public verifiability. In this paper, we present an efficient privacy-preserving machine learning scheme for multiple data providers. The proposed scheme allows all participants in the system model to publicly verify the correctness of the encrypted data. Furthermore, a unidirectional proxy re-encryption (UPRE) scheme is employed to reduce the high computational costs along with multiple data providers. The cloud server embeds noise in the encrypted data, allowing the analytics to apply machine learning techniques and preserve the privacy of data providers' information. The results and experiments tests demonstrate that the proposed scheme has the ability to reduce computational costs and communication overheads.
Classification of Multiparty Outsourced Data with Privacy Preservation
2016
Back-propagation Neural Network is one of the important machines learning technique for classification. Accuracy of any machine learning technique is improved with volume of datasets. Recent developments in computer networks provide such environment that multiple users connect with each other. This scenario leads in development of machine learning technique with collaborative or joint participation of these multiple users. In collaborative learning multiple parties participate jointly in learning where data is shared by users may contain sensitive information such as corporate data, health care data and personal data. There are chances of data leakage by any corrupt party or intruders. Users are concern about privacy of their datasets due to this main hurdle in collaborative machine learning technique many users are not interested to participate. In this project we are giving solution to privacy of individual users data by converting data in the form of cipher texts where users can ...
International Journal of Engineering Sciences & Research Technology, 2013
This paper presents a strategy for the use of cloud in Cheminformatics as a process of pharmaceutical Engineering for Analyzing Chemical Drug Molecules. The use of computer and informational techniques, applied to a range of problems in the field of Chemical Engineering using internet. These techniques are used in pharmaceutical companies in the process of drug discovery. These methods can also be used in chemical and allied industries in various other forms. The authors have recommended Cheminformatics pac which are like small molecule data. These tools can be helpful to obtain the effect of any drug on cells which can be further useful in cure of various diseases like cancer, swine flu etc. In addition these tools can be new molecule structure; it can be compared with existing molecules structures and also can show its 2D as well as 3D visualization. One of the Cheminformatics tools discussed in the paper named ChemMine Web Tool can be used on the internet without installing personalized software on their PC.
Privacy-Preserving Classification and Clustering Using Secure Multi-Party Computation
2000
Nowadays, data mining and machine learning techniques are widely used in electronic applications in different areas such as e-government, e-health, e-business, and so on. One major and very crucial issue in these type of systems, which are normally distributed among two or more parties and are dealing with sensitive data, is preserving the privacy of individual’s sensitive information. Each