Research On Medical Big Data Security And Privacy Protection Model Based On Risk Access Control

With the rapid development of the Internet,the Internet of Things,and cloud computing,artificial intelligence,cloud computing,and big data have become the three pillars of today's society from the information technology era to the data technology era.Big data technology has also become a major technical system after cloud computing.Its development not only covers distributed computing and distributed management,but also includes artificial intelligence,machine learning and other technologies.Big data technology has brought a lot of convenience to people's lives by continuously promoting the integration of information resources However,in the process of data collection,use,and sharing,it also brings great hidden dangers to people's privacy and security issues,and has drawn attention from all walks of life.Therefore,the security and privacy protection of big data has become one of the key issues to be solved urgently in big data technologyMedical big data as a national basic strategic resource has been formally incorporated into the national development strategy and has become a core asset in the medical field.According to the survey,most hospitals lack special privacy protection measures,and the medical industry has become one of the most serious areas of privacy leakage.Because of the special sensitivity of medical data,so it is necessary to study the security and privacy of medical industry.At present,the research on data security and privacy protection technology in academia mainly includes access control,data anonymization,data encryption,data traceability,differential privacy protection,digital watermarking,etc.Among them,access control technology has become the focus of current research,but it mainly focuses on the field of operating system,and there is not much research in the field of information,especially on the security and privacy protection of medical big data.In addition,because privacy protection work in a big data environment requires automated or semi-automated authorization management,traditional privacy protection models are difficult to adapt to this complex open environmentUnder the above background,this article perfects some shortcomings in the current medical big data security and privacy protection model,and proposes a medical big data security and privacy protection model based on risk access control In this model,user trust value is introduced to reduce the possibility of system misjudgment to a certain extent,and combines the self-learning ability of neural networks with the knowledge expression ability of fuzzy theory to establish an Adaptive Neuro-Fuzzy Inference System(ANFIS),which can dynamically predict user access risk.This article first reviews the research status of medical big data security and privacy protection and risk-based access control,and analyzes domestic and foreign research trends.After summarizing them,it is found that the current research on risk and access control is still in the initial exploration stage,and the research on privacy protection of medical big data based on risk access control is extremely scarceSecondly,this article not only discusses mandatory access control,autonomous access control,role-based access control,and attribute-based access control,but also analyzes its limitations in the big data environment and clarifies access control in the big data environment.The policy should satisfy the automated or semi-automated authorization management,and can be dynamically adjusted according to the actual scenario,thereby further introducing the data-based access control modelThen,through the literature review and expert consultation,the key indicators affecting the security and privacy of medical big data were analyzed from the user's perspective,including the user's access behavior and trust.Furthermore,based on the user's historical access information and interaction records,the user's access behavior and trust are quantified with the help of information entropy,probability,etc.,and a definition expression is given explicitly.In addition,this paper also summarizes the commonly used risk quantification methods and analyzes the advantages and disadvantages of them;then combines fuzzy theory and neural network to establish a risk quantification model based on adaptive neural fuzzy theory,and it is introduced in detail from three aspects:basic principles,network structure,and parameter learning principles for risk quantificationFinally,the entire experimental process and specific operations are introduced from three aspects:the experimental environment,the experimental data,and the experimental process.The prediction results of the model are compared with the actual output results with the help of Matlab.The experimental results found that the average error is less than 1e-5,indicating that the model in this paper is reliable in predicting the risk of medical big data security and privacy leakage.In addition,the method in this paper is compared with the current classic risk-based medical big data access control model.It is found that when the proportion of illegal users is less than 15%,the model in this paper is more superior in terms of accuracy and recall.