Software vulnerabilities pose a great threat to network and information security， and the root of vulnerabilities lies in software source code. Existing traditional static detection tools and deep learning based detection methods do not fully represent code features， and simply use word embedding method to transform code representation， so that their detection results have low accuracy and high false positive rate or high false negative rate. Therefore， a source code vulnerability detection method based on hybrid code representation was proposed to solve the problem of incomplete code representation and improve detection performance. Firstly， source code was compiled into Intermediate Representation （IR）， and the program dependency graph was extracted. Then， structural features were obtained through program slicing based on data flow and control flow analysis. At the same time， unstructural features were obtained by embedding node statements using doc2vec. Next， Graph Neural Network （GNN） was used to learn the hybrid features. Finally， the trained GNN was used for prediction and classification. In order to verify the effectiveness of the proposed method， experimental evaluation was performed on Software Assurance Reference Dataset （SARD） and real-world datasets， and the F1 score of detection results reached 95.3% and 89.6% respectively. Experimental results show that the proposed method has good vulnerability detection ability.

In power system， the trust evaluation of terminals is a key technology to grade the access and securely collect data， which is critical to ensure the safe and stable operation of the power grid. Traditional trust evaluation models usually calculate the trust score directly based on identification， running states and interaction histories， etc. of the terminals， and show poor performance with indirect attacks and node collusion. To address these problems， an Adaptive Interaction Feedback based Trust evaluation （AIFTrust） mechanism was proposed. In the proposed mechanism， device trust level was measured comprehensively based on direct trust evaluation module， trust recommendation module and trust aggregation module， and accurate trust evaluation for massive collaborative terminals in power information systems was achieved. First， the interaction cost was introduced by the direct trust evaluation module， and the direct trust score of the malicious target terminal was calculated on the basis of the trust decay policy. Then， the experience similarity was introduced by the trust recommendation evaluation module， and similar terminals were recommended through secondary clustering to improve the reliability of the recommendation trust scoring. After the above， the trust aggregation module was used to adaptively aggregate the direct trust score and the recommendation trust score based on the trust score accuracy. Simulation results on real datasets and synthetic datasets show that when attack probability is 30% and trust decay rate is 0.05， AIFTrust improves the recommendation accuracy by 13.30% and 14.81% compared to the similarity-based trust evaluation method SFM （Similarity FraMework） and the trust evaluation method based on objective information entropy CRT （Reputation Trusted based on Cooperation）， respectively.

Concerning the limitations that the accuracy of prediction is low and the classification on box-office is not significant in application, this paper proposed a new model to predict box-revenue of movie, based on the movie market in reality. The algorithm could be summarized as follows. Firstly, the factors that affected the box and format of the output were determined. Secondly, these factors should be analyzed and quantified within [0, 1]. Then, the number of neurons was also determined, aiming to build up the architecture of the neural network according to input and output. The algorithm and procedure were improved before finishing the prediction model. Finally, the model was trained with denoised historical movie data, and the output of model was optimized to dispel the randomness so that the result could reflect box more reliably. The experimental results demonstrate that the model based on back propagation neural network algorithm performs better on prediction and classification (For the first five weeks, the average relative error is 43.2% while the average accuracy rate achieves 93.69%), so that it can provide a more comprehensive and reliable suggestion for publicity and risk assessment before the movie is on, which possesses a better application value and research prospect in the prediction field.

To address the challenge of Android kernel hook detection, a new approach was proposed to detect Android kernel hooks by combining static technique based on characteristic pattern and dynamic technique based on behavioural analysis. The attacks including modifying system call tables and inline hook could be detected by the proposed approach. Software prototypes and test experiments were given. The experimental results show that the proposed method is effective and efficient in detecting Android kernel hooks, for most of the test cases, the runtime overhead is below 7%; and it is suitable to detect Android kernel hooks.

It has been proved that Physical Layer Network Coding (PLNC) can also improve the system throughput and spectral efficiency by taking the advantage of the broadcast nature of electromagnetic waves in wireless cooperative environments. In this paper, the basic idea of the PLNC was introduced and its benefit over traditional forward and straight-forward network coding under the two-way relay scenario was illustrated. Firstly, three types of physical layer network coding—Physical Network Coding over Finite Field (PNCF), Analog Network Coding (ANC) and Complex Field Network Coding (CFNC) were presented, the theory research development of the three kinds of PLNC were overviewed and new theory and technology related to it were introduced. Secondly, the application and implementation for the ANC scheme in the real wireless cooperative environments were overviewed. Finally, the opening issues and challenges for PLNC concerning both theory and implementation in near future were proposed．It is an important trend to improve the theory and implementation of PLNC, research the security of PLNC, and combine PLNC with other technologies, such as channel coding and modulation, relay choice, effective scheduling and resource allocation.