Data fusion is usually performed prior to classification in order to reduce the input space. These dimensionality reduction techniques help to decline the complexity of the classification model and thus improve the classification performance. The traditional supervised methods demand labeled samples, and the current network traffic data mostly is not labeled. Thereby, better learners will be built by using both labeled and unlabeled data, than using each one alone. In this paper, a novel network traffic data fusion approach based on Fisher and deep auto-encoder (DFA-F-DAE) is proposed to reduce the data dimensions and the complexity of computation. The experimental results show that the DFA-F-DAE improves the generalization ability of the three classification algorithms (J48, back propagation neural network (BPNN), and support vector machine (SVM)) by data dimensionality reduction. We found that the DFA-F-DAE remarkably improves the efficiency of big network traffic classification.

Currently, with the rapid increasing of data scales in network traffic classifications, how to select traffic features efficiently is becoming a big challenge. Although a number of traditional feature selection methods using the Hadoop-MapReduce framework have been proposed, the execution time was still unsatisfactory with numeral iterative computations during the processing. To address this issue, an efficient feature selection method for network traffic based on a new parallel computing framework called Spark is proposed in this paper. In our approach, the complete feature set is firstly preprocessed based on Fisher score, and a sequential forward search strategy is employed for subsets. The optimal feature subset is then selected using the continuous iterations of the Spark computing framework. The implementation demonstrates that, on the precondition of keeping the classification accuracy, our method reduces the time cost of modeling and classification, and improves the execution efficiency of feature selection significantly.

Network security situational assessment, the core task of network security situational awareness, can obtain security situation by comprehensively analyzing various factors that affect network status. Thus, network security situational assessment can provide accurate security state evaluation and security trend prediction for users. Although plenty of network security situational assessment methods have been proposed, there are still many problems to solve. First, because of high dimensionality of input data, computational complexity in model construction could be very high. Moreover, most of the existing schemes trade computational overhead for accuracy. Second, due to the lack of centralized standard, the weights of indicators are usually determined empirically or by subjective opinions of domain expert. To solve the above problems, we propose a novel network security situation assessment method based on stack autoencoding network and back propagation neural network. In stack autoencoding network and back propagation neural network, to reduce the data storage overhead and improve computational efficiency, we use stack autoencoding network to reduce the dimensions of the indicator data. And the low-dimensional data output by hidden layer of stack autoencoding network will be the input data of the error back propagation neural network. Then, the back propagation neural network algorithm is adopted to perform network security situation assessment. Finally, extensive experiments are conducted to verify the effectiveness of the proposed method.

User behavior threat detection is important for the protection of network system security. Traditional supervised modeling methods and unbalanced sample data lead to a high false positive rate in user behavior detection. In addition, network user behaviors are complex, changeable, and difficult to predict, and existing detection methods are facing ever greater challenges. Effectively detecting user behavior remains a challenge. In this paper, we propose a user behavior threat detection method based on an Adaptive Sliding Window Generative Adversarial Network(ASW-GAN). This method designs an adaptive sliding window mechanism to process behavior data and uses the GAN model to detect threat behavior, finally uses the maximum interclass variance algorithm Otsu to optimize test detection result. Compared with other typical methods, the proposed method achieves a higher accuracy rate and a markedly lower false positive rate, and can effectively evaluate user threat behaviors.

With the rapid development of cloud computing, an increasing number of data owners are willing to employ cloud storage service. In cloud storage, the resource-constraint data owners can outsource their large-scale data to the remote cloud server, by which they can greatly reduce local storage overhead and computation cost. Despite plenty of attractive advantages, cloud storage inevitably suffers from some new security challenges due to the separation of outsourced data ownership and its management, such as secure data insertion and deletion. The cloud server may maliciously reserve some data copies and return a wrong deletion result to cheat the data owner. Moreover, it is very difficult for the data owner to securely insert some new data blocks into the outsourced data set. To solve the above two problems, we adopt the primitive of Merkle sum hash tree to design a novel publicly verifiable cloud data deletion scheme, which can also simultaneously achieve provable data storage and dynamic data insertion. Moreover, an interesting property of our proposed scheme is that it can satisfy private and public verifiability without requiring any trusted third party. Furthermore, we formally prove that our proposed scheme not only can achieve the desired security properties, but also can realize the high efficiency and practicality.