Security issues have resulted in severe damage to the cloud computing environment, adversely affecting the healthy and sustainable development of cloud computing. Intrusion detection is one of the technologies for protecting the cloud computing environment from malicious attacks. However, network traffic in the cloud computing environment is characterized by large scale, high dimensionality, and high redundancy, these characteristics pose serious challenges to the development of cloud intrusion detection systems. Deep learning technology has shown considerable potential for intrusion detection. Therefore, this study aims to use deep learning to extract essential feature representations automatically and realize high detection performance efficiently. An effective stacked contractive autoencoder (SCAE) method is presented for unsupervised feature extraction. By using the SCAE method, better and robust low-dimensional features can be automatically learned from raw network traffic. A novel cloud intrusion detection system is designed on the basis of the SCAE and support vector machine (SVM) classification algorithm. The SCAE+SVM approach combines both deep and shallow learning techniques, and it fully exploits their advantages to significantly reduce the analytical overhead. Experiments show that the proposed SCAE+SVM method achieves higher detection performance compared to three other state-of-the-art methods on two well-known intrusion detection evaluation datasets, namely KDD Cup 99 and NSL-KDD.

The fine-grained classification of encrypted traffic is important for network security analysis. Malicious attacks are usually encrypted and simulated as normal application or content traffic. Supervised machine learning methods are widely used for traffic classification and show good performances. However, they need a large amount of labeled data to train a model, while labeled data is hard to obtain. Aiming at solving this problem, this paper proposes a method to train a model based on the K-nearest neighbor (KNN) algorithm, which only needs a small amount of data. Due to the fact that the importance of different traffic features varies, and traditional KNN does not highlight the importance of different features, this study introduces the concept of feature weight and proposes the weighted feature KNN (WKNN) algorithm. Furthermore, to obtain the optimal feature set and the corresponding feature weight set, a feature selection and feature weight self-adaptive algorithm for WKNN is proposed. In addition, a three-layer classification framework for encrypted network flows is established. Based on the improved KNN and the framework, this study finally presents a method for fine-grained classification of encrypted network flows, which can identify the encryption status, application type and content type of encrypted network flows with high accuracies of 99.3%, 92.4%, and 97.0%, respectively.

Nowadays, big data has become a hot research topic. It gives fresh impetus to the economic and social development. However, the huge value of big data also makes it the focus of attacks. Big data security incidents occur frequently in recent years. The security supervision capacities for big data do not match its important role. Data provenance which describes the origins of data and the process by which it arrived the current state, is an effective approach for data supervision. For the full use of provenance in big data supervision, a provenance model which defines the concepts used to represent the provenance types and relations is required to be built in advance, but current provenance models do not adapt to big data scenarios well. In this paper, we comprehensively consider the characteristics of big data and the requirements of data security supervision, extend the widely used provenance model PROV-DM by subtyping and new relation definition, and propose a big data provenance model (BDPM) for data supervision. BDPM model supports the provenance representation of various data types and diverse data processing modes to represent the entire data transformation process through different components in the big data system, and defines new relations to enrich provenance analysis functions. Based on BDPM model, we introduce the constraints that should be satisfied in the construction of valid provenance graph and present the data security supervision methods via provenance graph analysis. Finally, we evaluated the satisfiability of BDPM model through a case study.

The openness of Android operating system not only brings convenience to users, but also leads to the attack threat from a large number of malicious applications (apps). Thus malware detection has become the research focus in the field of mobile security. In order to solve the problem of more coarse-grained feature selection and larger feature loss of graph structure existing in the current detection methods, we put forward a method named DGCNDroid for Android malware detection, which is based on the deep graph convolutional network. Our method starts by generating a function call graph for the decompiled Android application. Then the function call subgraph containing the sensitive application programming interface (API) is extracted. Finally, the function call subgraphs with structural features are trained as the input of the deep graph convolutional network. Thus the detection and classification of malicious apps can be realized. Through experimentation on a dataset containing 11,120 Android apps, the method proposed in this paper can achieve detection accuracy of 98.2%, which is higher than other existing detection methods.

A remarkable characteristic of modern operating system is open, which means that we can download data or execute codes from any Internet sources whether they are trusted or not. As a consequence, there is a contradict situation when we want to use these data or codes as well as keep the system security. Despite decades of researches and experiences on this problem, it is still assumed as a great challenge. This paper presents a novel dynamic defense model (DDM) to reduce security risks brought by these suspicious data or codes for the open operating systems. DDM is a high-level security defense abstraction with four key minds: dynamic label marking, dynamic label tracking, dynamic label modulating, and run-time controlling. With these minds, DDM achieves the full, dynamic and real-time security protection in the whole life cycle of the operating system. We also practically implemented a prototype system named DDDroid on Android. We constructed a mixed experimental data set with 30 malware samples and 970 benign applications to test the defense effects of DDDroid. DDDroid detects 97% of the malware samples have malicious actions and blocks these actions with a negligible false positive on legal actions. We also demonstrated DDDroid is an effective system that prevents the sensitive data from being leaked by suspicious applications deliberately or by users unintentionally through some sample experiments. What’s more, with extensive evaluations, DDDroid is proved to be a system with low performance overhead and limited memory consumption.