Vulnerability is one of the root causes of network intrusion. An effective way to mitigate security threats is to discover and patch vulnerabilities before an attack. Traditional vulnerability detection methods rely on manual participation and incur a high false positive rate. The intelligent vulnerability detection methods suffer from the problems of long-term dependence, out of vocabulary, coarse detection granularity and lack of vulnerable samples. This paper proposes an automated and intelligent vulnerability detection method in source code based on the minimum intermediate representation learning. First, the sample in the form of source code is transformed into a minimum intermediate representation to exclude the irrelevant items and reduce the length of the dependency. Next, the intermediate representation is transformed into a real value vector through pre-training on an extended corpus, and the structure and semantic information are retained. Then, the vector is fed to three concatenated convolutional neural networks to obtain high-level features of vulnerability. Last, a classifier is trained using the learned features. To validate this vulnerability detection method, an experiment was performed. The empirical results confirmed that compared with the traditional methods and the state-of-the-art intelligent methods, our method has a better performance with fine granularity.

Vulnerabilities threaten the security of information systems. It is crucial to detect and patch vulnerabilities before attacks happen. However, existing vulnerability detection methods suffer from long-term dependency, out of vocabulary, bias towards global features or local features, and coarse detection granularity. This paper proposes an automatic vulnerability detection framework in source code based on a hybrid neural network. First, the inputs are transformed into an intermediate representation with explicit structure information using lower level virtual machine intermediate representation (LLVM IR) and backward program slicing. After the transformation, the size of samples and the size of vocabulary are significantly reduced. A hybrid neural network model is then applied to extract high-level features of vulnerability, which learns features both from convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The former is applied to learn local vulnerability features, such as buffer size. Furthermore, the latter is utilized to learn global features, such as data dependency. The extracted features are made up of concatenated outputs of CNN and RNN. Experiments are performed to validate our vulnerability detection method. The results show that our proposed method achieves excellent results with F1-scores of 98.6% and accuracy of 99.0% on the SARD dataset. It outperforms state-of-the-art methods.

Automated vulnerability detection is one of the critical issues in the realm of software security. Existing solutions to this problem are mostly based on features that are defined by human experts and directly lead to missed potential vulnerability. Deep learning is an effective method for automating the extraction of vulnerability characteristics. Our paper proposes intelligent and automated vulnerability detection while using deep representation learning and heterogeneous ensemble learning. Firstly, we transform sample data from source code by removing segments that are unrelated to the vulnerability in order to reduce code analysis and improve detection efficiency in our experiments. Secondly, we represent the sample data as real vectors by pre-training on the corpus and maintaining its semantic information. Thirdly, the vectors are fed to a deep learning model to obtain the features of vulnerability. Lastly, we train a heterogeneous ensemble classifier. We analyze the effectiveness and resource consumption of different network models, pre-training methods, classifiers, and vulnerabilities separately in order to evaluate the detection method. We also compare our approach with some well-known vulnerability detection commercial tools and academic methods. The experimental results show that our proposed method provides improvements in false positive rate, false negative rate, precision, recall, and F1 score.

Today, social networks are becoming increasingly popular and indispensable, where users usually have multiple accounts. It is of considerable significance to conduct user identity linkage across social networks. We can comprehensively depict diversified characteristics of user behaviors, accurately model user profiles, conduct recommendations across social networks, and track cross social network user behaviors by user identity linkage. Existing works mainly focus on a specific type of user profile, user-generated content, and structural information. They have problems of weak data expression ability and ignored potential relationships, resulting in unsatisfactory performances of user identity linkage. Recently, graph neural networks have achieved excellent results in graph embedding, graph representation, and graph classification. As a graph has strong relationship expression ability, we propose a user identity linkage method based on a heterogeneous graph attention network mechanism (UIL-HGAN). Firstly, we represent user profiles, user-generated content, structural information, and their features in a heterogeneous graph. Secondly, we use multiple attention layers to aggregate user information. Finally, we use a multi-layer perceptron to predict user identity linkage. We conduct experiments on two real-world datasets: OSCHINA-Gitee and Facebook-Twitter. The results validate the effectiveness and advancement of UIL-HGAN by comparing different feature combinations and methods.

We investigate the less-explored task of generating open-ended questions that are typically answered by multiple sentences. We first define a new question type ontology which differentiates the nuanced nature of questions better than widely used question words. A new dataset with 4,959 questions is labeled based on the new ontology. We then propose a novel question type-aware question generation framework, augmented by a semantic graph representation, to jointly predict question focuses and produce the question. Based on this framework, we further use both exemplars and automatically generated templates to improve controllability and diversity. Experiments on two newly collected large-scale datasets show that our model improves question quality over competitive comparisons based on automatic metrics. Human judges also rate our model outputs highly in answerability, coverage of scope, and overall quality. Finally, our model variants with templates can produce questions with enhanced controllability and diversity.