Fine-grained data authorization is essential for accomplishing the principle of least privilege in modern data governance. Existing approaches often rely on static policies or coarse-grained controls, which are inadequate for dynamic, task-specific scenarios. We propose a novel Task-Driven Fine-grained Authorization framework (TDFA) that automatically infers necessary data access permissions from natural language task descriptions. Our framework comprises two stages. First, the coarse-grained semantic filtering leverages embedding-based similarity to narrow down relevant data scope. Then, the fine-grained inference employs a prompt-engineered large language model (LLM) with reinforced fine-tuning. The resulting authorizations and their accompanying justifications ensure both interpretability and adaptability. We release a comprehensive benchmark dataset comprising schema information of 216 data tables and 973 annotated tasks including field-level authorizations and rationales. Experimental results show that our method achieves a new state-of-the-art performance.

The essence of knowledge representation learning is to embed the knowledge graph into a low-dimensional vector space to make knowledge computable and deductible. Semantic indiscriminate knowledge representation models usually focus more on the scalability on real world knowledge graphs. They assume that the vector representations of entities and relations are consistent in any semantic environment. Semantic discriminate knowledge representation models focus more on precision. They assume that the vector representations should depend on the specific semantic environment. However, both the two kinds only consider knowledge embedding in semantic space, ignoring the rich features of network structure contained between triplet entities. The MulSS model proposed in this paper is a joint embedding learning method across network structure space and semantic space. By synchronizing the Deepwalk network representation learning method into the semantic indiscriminate model TransE, MulSS achieves better performance than TransE and some semantic discriminate knowledge representation models on triplet classification task. This shows that it is of great significance to extend knowledge representation learning from the single semantic space to the network structure and semantic joint space.

Obtaining demographic attributes of online users is of great significance for retail marketing, targeted advertisement and many other scenarios. Users' wanderings on various websites and applications contains user preference on different items, and can be leveraged to infer one's private attributes. Existing studies usually focus on manually defined features, relationships in online social networks, or modeling global user preferences. However, attribute inference from the most common behavioral data (e.g., browsing history, shopping cart) is recently overlooked, and still requires further research. In this work, we propose a Topic-Enhanced Attentive Recurrent Neural Network (TEA-RNN) model to capture both local neighborhood-based features (with attentive RNN) and global patterns (with topic model) within user behaviors, and apply multi-task learning mechanism with weighted losses to further leverage the latent relationships within demographics. Experimental results on real-world datasets demonstrates the effectiveness of TEA-RNN by comparing with several commonly used baselines.

More and more work has focused on incorporating different kinds of literals into Knowledge Graph to promote the performance of knowledge embedding. These literals contain numeric literals, text literals, image literals and so on. These additional descriptions are connected to the entities through certain attributes. To incorporate numeric literals, some methods combine the embeddings of literals part with the traditional part - embeddings of entities. However, in the construction of literals embeddings, these existing methods consider the differences of these attributes: one dimension represents one attribute. But they ignore semantic meanings of attributes themselves. In this paper, we propose two methods to incorporate attributes semantics into knowledge graph embeddings from two perspectives: LiteralEAN and literalE-AT. They concatenate with the embeddings of numeric literals by different ways. Furthermore, their extension model LiteralE-C is also proposed as having a more comprehensive representation of attributes semantics. In an empirical study over two standard datasets FB15k and FB15k-237, we evaluate our models for link prediction. We demonstrate that they show an effective way to improve LiteralE and achieve state-of-the-art results. In ablation experiments, we find combined models do better than their singular counterparts in most cases.

Graph Neural Networks (GNNs) has been widely used to address the sparsity and cold start problems in recommendation system. By propagating embeddings from multi-hop neighbor nodes among the interaction graph and update target user and item embeddings, GNNs-based methods can achieve better recommendation performance. But those methods directly concatenate the output of each layer and ignore the different influences between different layers, and they simply use the inner product of the user and item’s embeddings to calculate the similarity and make recommendation based on it, which is insufficient to reveal the complex and nonlinear interactions.In this work, we propose to learn multi-order interactions between users and items and capture correlations between different-order information. We design a new recommendation framework MCCR, which treats each layer’s output as differentorder feature, and propose a multi-order interaction module to represent feature interactions. We adopt a multi-layer 3D CNN module to learn high-order interaction signals between users and items in an explicit approach. Through extensive experiments on three real-world datasets, which shows that MCCR evidently outperforms the state-of-the-art methods consistently.

In recent years, attribute-based access control (ABAC) is more and more popular because of its flexibility and fine-grained data management. However, manually configuring authorization policies in ABAC system is a time-consuming, labor-intensive, and tedious work. Many researchers explore the ways of automatically configuring authorization policies by parsing requirement specifications that are expressed in natural language. Previous works only focus on English and ignore the semantics of comparative relationship. In this paper, we propose a method based on Chinese including procedures of key words extraction, tag alignment and expression transformation. It can parse Chinese sentence into constraint expressions and authorization sign, by which ABAC system is able to configure authorization policies automatically. Our evaluation results show that it has good performance not only in the independent tests on each procedure but also in the systematic tests on the whole method.

Vulnerability is one of the main causes of network intrusion. An effective way to mitigate security threats is to find and repair vulnerabilities as soon as possible. Traditional vulnerability detection methods are limited by expert knowledge. Existing deep learning-based methods neglect the connection between semantic graphs and cannot effectively deal with the structure information. Graph neural network brings new insight into vulnerability detection. However, benign nodes on the graph account for a large proportion, resulting in vulnerability information could be disturbed by them. To address the limitations of existing vulnerability detection approaches, in this paper, we propose ACGVD, a vulnerability detection method by constructing a graph network with attention. We first combine multiple semantic graphs together to form a more comprehensive graph. We then adopt the Graph neural network instead of the sequence-based model to automatically analyze the comprehensive graph. In order to solve the problem that the vulnerability information could be covered up, we add a double-level attention mechanism to the graph model. We also add a novel classification layer to extract the high-level features of the code. To make the experiment more realistic, the model is trained over the latest published real-world dataset. The experiment results demonstrate that compared with state-of-the-art methods, our model ACGVD achieves 5.01%, 13.89%, and 8.27% improvement in accuracy, recall and F1-score, respectively.

The recommendation system is one of the effective tools to solve information overload. Most of the current deep learning recommendation algorithms only focus on the accuracy of the recommendation results by learning users’ preferences. However, the diversity of the recommendation results is neglected, resulting in homogeneous recommendation results, which reduces users’ satisfaction. Diversity can not only effectively avoid over-fitting, but also comprehensively consider multiple dimensions to improve the quality of recommendation results. Therefore, we propose a content-based re-ranking method (CBR) for recommendation systems. The proposed method can make full use of the data set, and effectively supplement and re-rank the recommended results produced by some deep learning algorithms based on the edge information such as tags to be recommended from different perspectives, thus can effectively improve the diversity while preserving the accuracy of recommendation results. Experimental results demonstrate the significant improvements of the proposed re-ranking method.

Knowledge graph Embedding can obtain the low-dimensional dense vectors, which helps to reduce the high dimension and heterogeneity of Knowledge graph (KG), and enhance the application of KG. Many existing methods focus on building complex models, elaborate feature engineering or increasing learning parameters, to improve the performance of embedding. However, these methods rarely capture the influence of intrinsic relevance and inner sequence of the relations in KG simultaneously, while balancing the number of parameters and the complexity of the algorithm. In this paper, we propose a concatenate knowledge graph embedding method based on relevance and inner sequence of relations (KGERSR). In this model, for each triple, we use two partially shared gates for head and tail entities. Then we concatenate these two gates to capture the inner sequence information of the triples. We demonstrate the effectiveness of the proposed KGERSR on standard FB15k-237 and WN18RR datasets, and it gives about 2

Abstract With the popularity of the Internet, some online news reading habits have gradually replaced traditional media devices. People can see a variety of news on mobile phones or web pages. The overloaded information makes it impossible for users to quickly get the news they want to see, so the existence of a news recommendation system is necessary. However, unlike other fields, the recommendation of news is time-sensitive, and the problem of sparse data makes traditional collaborative filtering algorithms invalid. There are many entities in the news, and the knowledge graph is a collection of a large number of entities. In this paper, we propose a KSR model (Knowledge-based Sequential Recommendation) which uses the knowledge graph as side information to enrich the feature representation of the news to calculate the user’s probability to click the forecasted news. KSR uses the knowledge graph to represent the entities in the news and uses a recurrent neural network to capture the sequential relationships in the news data to enrich the feature representation of the news. Because the different news that user has clicked have different relations with the news to be predicted, the attention model is introduced to calculate the weights. Finally, we conduct experiments on the existing dataset and results prove the efficacy of KSR over several baselines. Different contrast experiments also prove the effectiveness of each module of the model.

Knowing exact demographic attributes of users is crucial for human-computer interaction, intelligent marketing and automatic advertising. Ubiquitous sensor devices yield massive volumes of temporal data which hide a lot of valuable demographic information. In this paper, we bridge the gap between sensor data and demographic prediction to obtain real attributes of users from popular sensor devices: pedometer, which is widely used in mobile devices. We propose a novel model named Separated Embedding and Correlation Learning (SECL) for demographic prediction. Specifically, SECL first process the input data with a separated embedding layer to disentangle task-specific features for interference eliminating, and then capture the hidden correlations between different tasks via a correlation learning layer, finally the refined task-specific features are fed into a multi-task prediction layer to predict demographic attributes. Experimental results show impressive performance of our model on a real-world pedometer dataset, which is made publicly available on https://github.com/deepdeed/SECL.

Users’ real demographic attributes is impressively useful for intelligent marketing, automatic advertising and human-computer interaction. Traditional method on attribute prediction make great effort on the study of social network data, but ignore massive volumes of disparate, dynamic, and temporal data derived from ubiquitous mobile and sensor devices. For example, daily walking step counts produced by pedometer. Multiple demographic prediction on temporal data have two problems. First one is that differential effectiveness of different time period data for prediction is unclear. And another one is how to effectively learn the complementary correlations between different attributes. To address the above problem, we propose a novel model named Correlation-Aware Neural Embedding with Attention (CANEA), which first directly separates different attribute oriented feature using separated embedding layer, and use attention mechanism to assign a higher weight to dominant time point. Then it captures informative correlations using correlation learning layer. Finally we obtain the refined task-specific representations with optimal correlation information for predicting certain attributes. Experimental results show the effectiveness of our method.

Big data brings much convenience to our daily life, while it also raises concerns to personal information leakage. It is important for data owner to protect sensitive data from being attacked. In this paper, we elaborate on the possible attacks that may be suffered at various stages of personal data life cycle and the corresponding privacy protection methods. Based on these methods, a differential attribute desensitization system (DADS) for personal information protection has been proposed. Data owner can define sensitive attribute level in the DADS. And then DADS can automatically identify sensitive data, and take differentiated data desensitization measures for structured and unstructured multi-attribute information. Experimental results show that DADS can automatically adapt to different types of sensitive information and protect personal sensitive information effectively.

Due to rich characteristics and functionalities, PDF format has become the de facto standard for the electronic document exchange. As vulnerabilities in the major PDF viewers have been disclosed, a number of methods have been proposed to tame the increasing PDF threats. However, one recent evasion exploit is found to evade most of detections and renders all of the major static methods void. Moreover, many existing vulnerabilities identified before can now evade the detection through exploiting this evasion exploit. In this paper, we introduce this newly identified evasion exploit and propose a new feature extractor FEPDF to detect malicious PDFs. Based on the FEPDF and the JavaScript detection model, we test the performance of the proposed feature extractor FEPDF, and evaluation results show that FEPDF has a satisfactory performance in malicious PDF detection.

We present the EKNOT system that automatically discovers major events from online news articles, connects each event to its discussion in Twitter, and provides a comprehensive summary of the events from both news media and social media's point of view. EKNOT takes a time period as input and outputs a complete picture of the events within the given time range along with the public opinions. For each event, EKNOT provides multi-dimensional summaries: a) a summary from news for an objective description; b) a summary from tweets containing opinions/sentiments; c) an entity graph which illustrates the major players involved and their correlations; d) the time span of the event; and e) an opinion (sentiment) distribution. Also, if a user is interested in a particular event, he/she can zoom into this event to investigate its aspects (sub-events) summarized in the same manner. EKNOT is built on real-time crawled news articles and tweets, allowing users to explore the dynamics of major events with minimal delays.

We propose a single unified minimax entropy approach for user preference modeling with multidimensional knowledge. Our approach provides a discriminative learning protocol which is able to simultaneously a) leverage explicit human knowledge, which are encoded as explicit features, and b) model the more ambiguous hidden intent, which are encoded as latent features. A latent feature can be carved by any parametric form, which allows it to accommodate arbitrary underlying assumptions. We present our approach in the scenario of check-in preference learning and demonstrate it is capable of modeling user preference in an optimized manner. Check-in preference is a fundamental component of Point-of-Interest (POI) prediction and recommendation. A user's check-in can be affected at multiple dimensions, such as the particular time, popularity of the place, his/her category and geographic preference, etc. With the geographic preferences modeled as latent features and the rest as explicit features, our approach provides an in-depth understanding of users' time-varying preferences over different POIs, as well as a reasonable representation of the hidden geographic clusters in a joint manner. Experimental results based on the task of POI prediction/recommendation with two real-world check-in datasets demonstrate that our approach can accurately model the check-in preferences and significantly outperforms the state-of-art models.

A major event often has repercussions on both news media and microblogging sites such as Twitter. Reports from mainstream news agencies and discussions from Twitter complement each other to form a complete picture. An event can have multiple aspects (sub-events) describing it from multiple angles, each of which attracts opinions/comments posted on Twitter. Mining such reflections is interesting to both policy makers and ordinary people seeking information. In this paper, we propose a unified framework to mine multi-aspect reflections of news events in Twitter. We propose a novel and efficient dynamic hierarchical entity-aware event discovery model to learn news events and their multiple aspects. The aspects of an event are linked to their reflections in Twitter by a bootstrapped dataless classification scheme, which elegantly handles the challenges of selecting informative tweets under overwhelming noise and bridging the vocabularies of news and tweets. In addition, we demonstrate that our framework naturally generates an informative presentation of each event with entity graphs, time spans, news summaries and tweet highlights to facilitate user digestion.