With the rapid growth of machine learning and artificial intelligence in medical cloud systems, cloud-aided medical computing has materialized a concrete platform for rapid realization of the service-oriented computing paradigm. However, using machine learning approaches in medical clouds might cause serious privacy leakage risk, for example, it needs to take the patients’ sensitive data as the inputs of the machine learning algorithm. In this article, we propose an efficient and privacy-preserving clinical diagnosis scheme that was performed by an (untrusted and malicious) outsourced cloud platform, which can provide the diagnosis assistance for doctors without leaking any sensitive information of patients and service providers. Concretely, we give the security model of privacy-preserving multiclass support vector machine (SVM) in outsourced medical clouds and design a secure clinical diagnosis scheme with privacy-preserving multiclass predecision and diagnosis. We propose a novel encoding approach to implement the encryption of negative number, and design several security building blocks, such as privacy-preserving decision function computing, privacy-preserving classification, and search of max decision function on encrypted fields, to provide the construction of the secure clinical diagnosis with privacy-preserving multiclass SVM. We give the concrete scheme and provide the experiment on Dermatology datasheet. Security analysis and experimental results indicate that the proposed scheme is efficient and practical in privacy-preserving clinical diagnosis systems.

With the proliferation of cloud computing, data owners can outsource the spatial data from the Internet of Things devices to a cloud server to enjoy the pay-as-you-go storage resources and location-based services. However, the outsourced services may raise privacy concerns, since the cloud server may not be fully trusted for both data owners and search users. If the data owners and search users conventionally encrypt the spatial data and query requests, the efficiency and functionality of query processing are weakened. Most of the existing works only focus on spatial data search or keyword search and do not consider spatial keyword search over encrypted data. In this article, we first design a geometric range query (GRQ) scheme, which can generate an arbitrary geometric range to fit the search user’s desired spatial data while protecting location privacy. Furthermore, based on GRQ, we propose a multidimensional spatial keyword similarity search scheme with access control (MSSAC) by integrating the polynomial function and matrix transformation. Specifically, an access control strategy is defined by a role-based polynomial function, which is embedded in the vectors of indices and trapdoors to achieve efficient and lightweight access control. Moreover, MSSAC enables the cloud server to execute compute-then-compare operations for spatial keyword search in a privacy-preserving manner by leveraging techniques of randomizable permutation and matrix multiplication. The formal security analyses and extensive experiments demonstrate that GRQ and MSSAC preserve the privacy of data owners and search users while achieving efficient spatial keyword search.

The emergence of the beyond 5G (B5G) mobile networks has provided us with a variety of services and enriched our lives. The B5G super-heterogeneous network systems and highly differentiated application scenarios require highly elastic and endogenous information security, including network trust, security, and privacy. However, security issues have also been raised, which greatly threaten our information security and privacy. For example, malwares use domain generation algorithms (DGAs) to generate huge quantities of domain names and then induce users to access to steal private information, which greatly threatens our information security. In this paper, we propose an approach to detect the malicious domain name by extracting and analyzing the features using deep neural network. Unlike traditional algorithms that are generally built on tedious feature engineering, our paper utilizes the hierarchy of bidirectional recurrent neural networks (HBiRNN) to extract effective semantic features instead of traditional methods. We use the discriminator based on HBiRNN (D-HBiRNN) to detect malicious websites. This experiment verifies the validity of the algorithm and compares it with the traditional algorithm based on feature engineering. Moreover, the superiority of the algorithm is proved.

Question answering (QA) is a hot field of research in Natural Language Processing. A big challenge in this field is to answer questions from knowledge-dependable domain. Since traditional QA hardly satisfies some knowledge-dependable situations, such as disease diagnosis, drug recommendation, etc. In recent years, researches focus on knowledge-based question answering (KBQA). However, there still exist some problems in KBQA, traditional KBQA is limited by a range of historical cases and takes too much human labor. To address the problems, in this paper, we propose an approach of knowledge graph based question answering (KGQA) method for medical domain, which firstly constructs a medical knowledge graph by extracting named entities and relations between the entities from medical documents. Then, in order to understand a question, it extracts the key information in the question according to the named entities, and meanwhile, it recognizes the questions’ intentions by adopting information gain. The next an inference method based on weighted path ranking on the knowledge graph is proposed to score the related entities according to the key information and intention of a given question. Finally, it extracts the inferred candidate entities to construct answers. Our approach can understand questions, connect the questions to the knowledge graph and inference the answers on the knowledge graph. Theoretical analysis and real-life experimental results show the efficiency of our approach.

Since Android has become the dominator of smartphone operating system market with a share of 86.8%, the number of Android malicious applications are increasing rapidly as well. Such a large volume of diversified malware variants has forced researchers to investigate new methods by using machine learning since it provides a powerful ability for variants detection. Since the static analysis of malware plays an important role in system security and the opcode has been shown as an effective representation of malware, some of them use the Dalvik opcodes as features of malware and adopt machine learning to detect Android malware. However, current opcode-based methods are also facing some problems, such as considering both of accuracy and time cost, selection of features, and the lack of understanding or description of the characteristics of malware. To overcome the existing challenges, we propose a novel method to build a graph of Dalvik opcode and analyze its global topology properties, which will first construct a weighted probability graph of operations, and then we use information entropy to prune this graph while retaining information as more as possible, the next we extract several global topology features of the graph to represent malware, finally search the similarities with these features between programs. These global topology features formulate the high-level characteristics of malware. Our approach provides a light weight framework to detect Android malware variants based on graph theory and information theory. Theoretical analysis and real-life experimental results show the effectiveness, efficiency, and robustness of our approach, which achieves high detection accuracy and cost little training and detection time.