Fake news detection aims to detect fake news widely spreading on social media platforms, which can negatively influence the public and the government. Many approaches have been developed to exploit relevant information from news images, text, or videos. However, these methods may suffer from the following limitations: (1) ignore the inherent emotional information of the news, which could be beneficial since it contains the subjective intentions of the authors; (2) pay little attention to the relation (similarity) between the title and textual information in news articles, which often use irrelevant title to attract reader' attention. To this end, we propose a novel Title-Text similarity and emotion-aware Fake news detection (TieFake) method by jointly modeling the multi-modal context information and the author sentiment in a unified framework. Specifically, we respectively employ BERT and ResNeSt to learn the representations for text and images, and utilize publisher emotion extractor to capture the author's subjective emotion in the news content. We also propose a scale-dot product attention mechanism to capture the similarity between title features and textual features. Experiments are conducted on two publicly available multi-modal datasets, and the results demonstrate that our proposed method can significantly improve the performance of fake news detection. Our code is available at https://github.com/UESTC-GQJ/TieFake.

VPN has posed many difficulties for network security management. In this paper, we develop a robust method to classify the VPN traffic. Firstly, we investigate the VPN transmission process and find the turning packet interval (Named as TPI) is a valuable feature for VPN traffic classification. Then we employ the probability distribution of TPI to improve the robustness of classification process, which is named as TPIPD. Secondly, we evaluate our method using the ISCXVPN2016 dataset and find our method has higher classification accuracy compared with other related methods. We also find the distribution of the first few TPIs can be used to represent that of the entire TPIs of specific flow, thus our method can be used for online traffic classification. As TPIPD is a kind of probability feature, it is more robust than other traditional features. Finally, the experiments verify our methods can be used for mice flow identification.

Rumors can spread very rapidly through online social networks (OSNs), leading to huge negative impact on human society. Hence, there is an urgent need to develop models that can minimize the spread of rumors. In this article, we propose a novel framework to improve the cost and efficiency of rumor propagation control. First, to reduce the impact of rumor controlling mechanism on users’ normal activities, we introduce a soft dynamic quarantine strategy into rumor propagation control and develop a new propagation model named susceptible-infected-removed-quarantined ignorants-quarantined spreaders (SIRQU) to model and block the rumor propagation in the network. Second, to further improve the control efficiency, we propose an influential node selection algorithm based on discrete particle swarm optimization with an evolutionary search strategy, and the controlling mechanism is only applied on the most influential nodes. Finally, we conduct a series of simulations and experiments on several public datasets and the dataset collected from Sina Weibo to validate the proposed method, and the results show that the proposed method outperfoms the related baseline algorithms.

With the development of smart mobile devices, location privacy has gained attention from both academia and industry. In recent years, a variety of location privacy definitions from different perspectives have been proposed to quantify location privacy and compare location privacy protection mechanisms (LPPMs). These definitions, however, have some drawbacks. In this paper, we propose a location privacy metric for discrete location information which improves the quantification of distance between the prior and posterior distribution of an adversary who may hold background knowledge in differential privacy. Furthermore, we develop a non-convex optimization problem and construct a near-optimal mechanism. We evaluate our proposed metric by comparing it to the state-of-the-art definitions including Shokri's incorrectness, Andrés's geo-indistinguishability and Dong's DPLO. We also evaluate our proposed mechanism with the optimal mechanisms based on the afore mentioned existing definitions. We make experiments on both simulation and realworld dataset, and the results show that our proposed metric and mechanism have the ascendant position.

In Wi-Fi networks, devices can be identified by physical features or MAC layer features, and the solutions of device identification can be used to enhance device authentication. Since 802.11ac Standard has been widely applied in Wi-Fi devices in recent years, the traditional identification methods designed for 802.11b/g/n devices will be no longer applicable. Therefore, it is necessary to design the corresponding 802.11ac device identification method. Compared with the physical feature-based method, the MAC layer-based method has advantages of low cost and easy deployment, so it has attracted more and more researchers' attention. In this paper, we use the fields from 802.11ac MAC frame as fingerprints. Through the analysis of 802.11ac MAC frame, a preprocessing method of the frame is proposed to mask strong and easy-to-modified identifiers. Then to overcome the difficulties caused by random changes in field values, we propose a device identification method based on the deep learning to select features automatically. Compared with the previous one using the transmitting rate as a feature, our method does not spend much time capturing packets in the device identification stage and has better performance whose average precision and recall exceed 99%.

Summary Dual‐hop 60 GHz wireless networks which support relay‐assisted dual‐hop transmission have been widely adopted in the recent years, aiming to prolong communication distance and bypass obstacles in 60 GHz band. However, it is very challenging to perform link scheduling in such dual‐hop architecture while considering several factors, i.e., reducing network power consumption, avoiding overloaded APs/relays and adapting to network dynamics. To this end, we investigate the problem of energy‐efficient link scheduling with load constraints (ELL), and propose solutions to deal with network dynamics. First, we present a fine‐grained energy model for dual‐hop 60 GHz networks, and formulate the ELL problem as an integer linear programming model that aims to minimize the network power consumption, while satisfying AP/relay load constraints. Then, we propose a polynomial‐time global scheduling algorithm that obtains a near‐optimal link scheduling solution via iterative relaxation, and the load constraint at each AP/relay can only be violated by at most an additive constant of two. Moreover, we present a local adjustment algorithm to adjust link‐scheduling solutions efficiently, such as client arrival/departure and link blockage, and design a hybrid algorithm that combines global scheduling and local adjustment. Finally, we conduct simulation experiments that validate our algorithms' effectiveness and efficiency.

Data anonymization is widely used to preserve the utility of published datasets without compromising privacy. The state-of-the-art data anonymization approaches are mainly single-record-based algorithms. They group similar records together one by one, then form equivalence classes through generalization. However, these algorithms didn't utilize equivalence classes which exist in the raw dataset. In this paper, we propose a new concept named natural equivalent class. It refers to the record set with the same quasi-identifier values naturally existing in the raw dataset. We theoretically prove that the natural equivalent class can effectively reduce the computational complexity of clustering algorithms as well as information loss. Then, we propose a novel clustering-based anonymization algorithm, which tries to cluster records without separating any natural equivalent class. Extensive experiments on real world datasets show that our approach outperforms the previous clustering-based anonymization algorithms in terms of efficiency and data utility.

Analyzing the popularity of microblogging services is of great significance in various applications. The number of posts provides novel insights into the popularity of microblogging services, and is critical to learn about the frequency of use. Existing approaches analyze this parameter by observing posts published by a large number of users, which may lead to underestimate the value since the sampled user may stop to use the service during the observing process. In this paper, we propose a novel method to estimate the number of posts in microblogging services. The basic idea behind this method is to make use of a common API provided by microblogging services, i.e., the public_timeline API. Posts sampled by this API may duplicate among multiple invocations, so the capture-recapture model can be used to estimate the total number of posts. Based on the traditional capture-recapture model, we propose an improved model to address challenges on low sampling probability and unequal sampling probability. We validate the proposed method using a real life Sina Weibo dataset, and the experimental results demonstrate the effectiveness and accuracy of our proposed method.

Although a variety of anonymization approaches have been proposed to achieve anonymity during data sharing, few of them can handle incomplete microdata, i.e. microdata with missing values. Directly applying existing approaches to incomplete microdata will incur extensive information loss, due to the existence of missing values. In this paper, we formulate this problem as missing value pollution, and analysis its influences on generalization based algorithms. Then we propose two top-down algorithms named Enhanced Mondrian and Semi-Partition, which achieve high data utility on incomplete microdata. Extensive experiments on real-world data show the effectiveness of our approach.