Rencent advancements in large language models (LLM) have shown impressive versatility across various tasks.Short text matching is one of the fundamental technologies in natural language processing.In previous studies, the common approach to applying them to Chinese is segmenting each sentence into words, and then taking these words as input.However, existing approaches have three limitations: 1) Some Chinese words are polysemous, and semantic information is not fully utilized.2) Some models suffer potential issues caused by word segmentation and incorrect recognition of negative words affects the semantic understanding of the whole sentence.3) Fuzzy negation words in ancient Chinese are difficult to recognize and match.In this work, we propose a novel adaptive Transformer for Chinese short text matching using Data Augmentation and Semantic Awareness (DASA), which can fully mine the information expressed in Chinese text to deal with word ambiguity.DASA is based on a Graph Attention Transformer Encoder that takes two word lattice graphs as input and integrates sense information from N-HowNet to moderate word ambiguity.Specially, we use an LLM to generate similar sentences for the optimal text representation.Experimental results show that the augmentation done using DASA can considerably boost the performance of our system and achieve significantly better results than previous state-of-theart methods on four available datasets, namely MNS, LCQMC, AFQMC, and BQ.

Remote photoplethysmography (rPPG) estimates heart rate by capturing blood volume pulse (BVP) signals from subtle pixel variations in video frames. This study presents a novel approach that leverages facial physiological characteristics to improve heart rate estimation. Specifically, we introduce a method for extracting Identity-Specific Facial Contours (ISFCs) and utilize a self-learning combination mechanism that directs the model’s attention to these ISFCs, resulting in significant improvements in both accuracy and robustness. Our rFaceNet model effectively extracts ISFCs from temporally normalized frames using a Temporal Compressor Unit (TCU) and refines focus on relevant facial regions via a Cross-Task Feature Combiner (CTFC). Through meticulous training, rFaceNet significantly enhances the quality and interpretability of facial physiological signals when compared to previous approaches. Moreover, our method outperforms State-of-the-Art (SOTA) models across various heart rate estimation benchmarks.

Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the semantic relationship before and after the sentence after integrating lexical information. Therefore, the regularity of word length information has not been fully explored in various word-character fusion methods. In this work, we propose a Lexicon-Attention and Data-Augmentation (LADA) method for Chinese NER. We discuss the challenges of using existing methods in incorporating word information for NER and show how our proposed methods could be leveraged to overcome those challenges. LADA is based on a Transformer Encoder that utilizes lexicon to construct a directed graph and fuses word information through updating the optimal edge of the graph. Specially, we introduce the advanced data augmentation method to obtain the optimal representation for the NER task. Experimental results show that the augmentation done using LADA can considerably boost the performance of our NER system and achieve significantly better results than previous state-of-the-art methods and variant models in the literature on four publicly available NER datasets, namely Resume, MSRA, Weibo, and OntoNotes v4. We also observe better generalization and application to a real-world setting from LADA on multi-source complex entities.

In view of the concealment and destructiveness of insider threats, to detect insider threats is very important for protecting the security of enterprises and organizations. Especially for complex insider threat scenarios, current detection methods still have many limitations. Although log-based cyber threat hunting may be an effective solution, non-trivial efforts of manual query construction hinder its use. In this paper, we propose a stream-based smart query system for real-time threat hunting within enterprise (SPYRAPTOR). Built upon system auditing frameworks, SPYRAPTOR constructs a threat behavior graph based on historical anomalous audit data and information on personnel and asset of the enterprise. An Insider Threat Query Language (ITQL) and an ITQL query synthesis mechanism are provided to synthesize the ITQL query strategy of insider threat scenarios based on the threat behavior graph. An efficient query execution system parses ITQL queries and implement real-time hunting of insider threat scenarios on the stream processing engine. We conduct experiments based on the CERT dataset and the results show that SPYRAPTOR achieves an excellent performance (precision of 0.91, recall of 0.89 and low detection latency) and outperforms the state-of-the-art methods.

The Practical Byzantine Fault Tolerance (PBFT) consensus in permissioned blockchains is known for its strong consistency and engineering feasibility. However, research on dynamic node join/leave processes and robustness is limited. This study presents an active removal dynamic PBFT algorithm, utilizing atomic broadcast technology for a provably secure dynamic broadcast primitive and a K-Nearest Neighbors (KNN) based malicious node classification and removal protocol. This enables PBFT consensus to accommodate dynamic requirements while mitigating voting power attacks and malicious nodes. Results show maintained system performance during dynamic node changes, accurate malicious behavior detection, and prompt node removal, addressing current PBFT limitations and enhancing blockchain network robustness.

The network security architecture of 5G defined by 3rd Generation Partnership Project (3GPP) in version 15, is vulnerable to the attack on wireless transmission due to its imperfect security design. The Distributed Denial of Service (DDoS) Attack is currently one of the biggest threats to air interface security of 5G. Attackers use controlled equipment to send a large number of authentication signaling to target base station, forming an instantaneous DDoS attack to achieve the purpose of destroying available resources. DDoS attack is simple to operate, hard to detect, and hugely harmful. From the perspective of signaling changes, this paper focuses on analyzing the authentication process that is most prone to DDoS attack, and extracts seven features based on the signaling change of the authentication process. We innovatively establish a classifier to detect DDoS attack using a novel improved naive Bayes algorithm. The algorithm not only comprehensively considers the independency and dependency between features through structural improvement, but also uses genetic algorithm to solve the optimal combination of attributes for category weights. At the end of the paper, we give simulation results which show the effectiveness of the proposed algorithm in detecting DDoS attack.

With the advancements in Machine Learning (ML) and edge computing, increasing efforts have been devoted toedge video analytics. However, most of the existing works fail to consider the cooperation of edge nodes for ML model caching and video frame scheduling, thus less efficient in practical scenarios with diverse requirements. In this article, we propose a novel approach named ESMO (joint framEScheduling andMOdel caching) to jointly optimize Frame Scheduling and Model Caching (FSMC), aiming at enhancing the performance of edge video analytics. In detail, we decompose the FSMC as three sub-problems, where the first two sub-problems (i.e., user's transmit power and edge computing resources allocation problems) are proven to be quasi-convex and strictly convex, respectively; while the third main sub-problem (i.e., trade-off among the video analytics (VA) accuracy, service delay and energy consumption) is NP-hard. Therefore, an efficient Two-layers Genetic Algorithm based algorithm (i.e., TGA-FSMC) is designed to find the close-to-optimal frame scheduling and the model caching decisions in an iterative manner. Finally, we deploy a target recognition prototype to comprehensively evaluate the practical performance in diverse edge nodes and CNN models. Extensive experiments demonstrate the empirical superiority of the ESMO over alternatives on real-world edge video analytics platforms, and it achieves 37.5%$\sim$87.2% performance improvement.

The subtle and dynamic nature of insider threat makes it one of the most challenging problems in cyber security domain. Most of the existing studies model the problem from the perspective of user behavior, but the imbalance of data categories and the weak correlation between discrete behaviors are not considered simultaneously. To address these problems, we use reinforcement learning-based Generative Adversarial Network to synthesize high-quality minority class data, and use Word2Vec language model to learn the distance metric between different behaviors. In this paper, we propose a Resource Access Pattern Network (RAP-Net), which applies reinforcement learning-based Generative Adversarial Network, Word2Vec, Convolutional Neural Network, Recurrent Neural Network, and Attention Mechanism to insider threat detection. RAP-Net extracts user resource access pattern sequences from audit log files, and then performs data augmentation on the minority class sequences. After learning the distance metric of different tokens in sequences, feature vectors are sent to the classifier for anomaly detection. RAP-Net successfully addresses two major pain points in the current field, namely data imbalance and weak correlation of discrete behaviors. Intensive experimental results on the CMU-CERT r4.2 dataset demonstrate that RAP-Net outperforms state-of-the-art studies in the field.

Third-party libraries (TPLs) are a significant component of mobile apps. They provide various functionalities, and developers employ them to facilitate app development. TPL detection is a fundamental task in security research, as it can impact other security studies. TPL can act as an assistant to malware detection, privacy leakage detection, etc. Because if a TPL carries malicious code, all apps that integrate the TPL can be considered risky. However, in some studies, TPLs can also act as noise, like app traffic fingerprinting. The TPL and app traffic are mixed during app runtime, making it difficult to fingerprint the app traffic accurately. Unfortunately, all existing TPL detection studies are working with prior knowledge of TPLs, as they need a whitelist or a train on known TPLs. However, new TPLs keep emerging, and it is not feasible for existing works to identify them-especially those who have network behaviors, as they may transfer inappropriate contents in the network. To this end, we propose LibHunter - an approach to identify TPLs without prior knowledge. LibHunter inspects the HTTP(S) traffic, logs the corresponding code execution traces, extracts features from the collected data, and performs a clustering algorithm to obtain TPLs. We apply LibHunter to 3000 apps. Results demonstrate that LibHunter can identify 79 TPLs, and about 60% of them are not detected by all existing works. We perform an analysis to show how important these TPLs are; we also present the visiting graph of these TPLs. Our findings bring light to the research community that existing tools are not accurate when encountering contemporary apps.

The biometric technology of heart signal has always been an important research direction of identity recognition. In this paper, we propose a method for heart rate signal extraction and identification based on speckle images. It contains two parts: contactless heart rate signal acquisition and identification. Irradiate the human body with laser to get speckle images, and obtain the heart rate signal by image correlation and filtering. Next, build a dataset with signals and the convolutional neural network model is used to realize the identification. The experimental results show that, the speckle image correlation method can achieve heart rate signal extraction in places where the pulse vibration is weak. In addition, compared with k- Nearest Neighbor and random forest, the convolutional neural model is more accurate in identification. The model achieved an accuracy of 87.33 % on the dataset, which confirms that it is effective for identification based on non-contact heart rate signal.

Remote speech reconstruction is widely used in counter-terrorism, medical science and engineering. In order to obtain reconstructed speech with high accuracy, we propose a speech reconstruction method. This method consists of two parts. Firstly, some optical devices are used to collect speckle images. Secondly, the convolutional neural network is used to detect the subtle motion of speckles. The results show that the lowest mean absolute error of the sinusoidal signal reconstructed by the method is 0.0489, and the lowest mean absolute error of the real speech is 0.0271. Compared with the convolutional neural network proposed before, the error of reconstructed speech is small, and the number of parameters is significantly reduced, with 0.73M for our model compared to 11.45M for the previous model. Besides, the time cost of training on some datasets is reduced to less than 1 hour, which is much lower than the previous model. The experimental results prove that our model is a lightweight, high-accuracy model for remote speech reconstruction with short training time.

In view of the concealment and destructiveness of insider threats, to detect insider threats is very important for protecting the security of enterprises and organizations. However, it is still a challenge to design a practical detection scheme which can accurately mine abnormal clues and has a high level of automation. In this paper, we propose the Behavior Sequence Network (BS-Net) which applies the one-class support vector machine and the recurrent neural network to the insider threat detection problem. The BS-Net is a detection framework based on user behavior portrait that learns representative features from the raw log data and then makes discrimination by a unified standard. Through a flow sequence division method, the original data flow is divided into short sequences. After behavior feature extraction and sequence matching, behavior sequences are sent into two anomaly detection models to analyze the occurrence possibility of behaviors from local detail features and the global dependence relationship between businesses respectively. We conduct experiments based on the CERT dataset and the results show that BS-Net achieves an excellent performance (recall rate of 0.94, accuracy of 0.94, and FPR of 0.12) and outperforms the state-of-the-art methods.

In remote regions (e.g., mountain and desert), cellular networks are usually sparsely deployed or unavailable. With the appearance of new applications (e.g., industrial automation and environment monitoring) in remote regions, resource-constrained terminals become unable to meet the latency requirements. Meanwhile, offloading tasks to urban terrestrial cloud (TC) via satellite link will lead to high delay. To tackle above issues, Satellite Edge Computing architecture is proposed, i.e., users can offload computing tasks to visible satellites for executing. However, existing works are usually limited to offload tasks in pure satellite networks, and make offloading decisions based on the predefined models of users. Besides, the runtime consumption of existing algorithms is rather high. In this paper, we study the task offloading problem in satellite-terrestrial edge computing networks, where tasks can be executed by satellite or urban TC. The proposed Deep Reinforcement learning-based Task Offloading (DRTO) algorithm can accelerate learning process by adjusting the number of candidate locations. In addition, offloading location and bandwidth allocation only depend on the current channel states. Simulation results show that DRTO achieves near-optimal offloading cost performance with much less runtime consumption, which is more suitable for satellite-terrestrial network with fast fading channel.

Mobile edge computing (MEC) has been envisaged as one of the most promising technologies in the fifth generation (5G) mobile networks. It allows mobile devices to offload their computation‐demanding and latency‐critical tasks to the resource‐rich MEC servers. Accordingly, MEC can significantly improve the latency performance and reduce energy consumption for mobile devices. Nonetheless, privacy leakage may occur during the task offloading process. Most existing works ignored these issues or just investigated the system‐level solution for MEC. Privacy‐aware and user‐level task offloading optimization problems receive much less attention. In order to tackle these challenges, a privacy‐preserving and device‐managed task offloading scheme is proposed in this paper for MEC. This scheme can achieve near‐optimal latency and energy performance while protecting the location privacy and usage pattern privacy of users. Firstly, we formulate the joint optimization problem of task offloading and privacy preservation as a semiparametric contextual multi‐armed bandit (MAB) problem, which has a relaxed reward model. Then, we propose a privacy‐aware online task offloading (PAOTO) algorithm based on the transformed Thompson sampling (TS) architecture, through which we can (1) receive the best possible delay and energy consumption performance, (2) achieve the goal of preserving privacy, and (3) obtain an online device‐managed task offloading policy without requiring any system‐level information. Simulation results demonstrate that the proposed scheme outperforms the existing methods in terms of minimizing the system cost and preserving the privacy of users.

With the rapid growth of multimedia content in the social content-centric network (SocialCCN), in-network caching and caching strategy are becoming more and more important for efficient content delivery, but it also brings huge challenges to the cache space and computing capabilities in the network. In order to increase cache space and improve the computing capability in SocialCCN, in this paper, we integrate Mobile edge computing with SocialCCN (MeSoCCN) and design a novel caching strategy in MeSoCCN. Firstly, we proposed MeSoCCN, a novel architecture that integrates Mobile Edge Computing (MEC) in SocialCCN. Then, in MeSoCCN, a caching strategy based on popularity prediction is designed, which can increase the cache hit rate and reduce hop redundancy. We predict content popularity in the future and make cache placement and replacement decisions based on the prediction results. Finally, we conducted experiments and verified the effectiveness of the proposed caching strategy in MeSoCCN.

Anomaly detection on attributed networks aims to differentiate rare nodes that are significantly different from the majority. It plays an important role in various practical scenarios, such as intrusion detection and fraud detection. However, existing graph-based methods mainly adopt shallow models that cannot capture the highly non-linear interactions between nodes in an attribute network consisting of different information modalities. To tackle the above issues, in this paper, we propose a novel deep model named DeepAE for anomaly detection which (a) can capture the high non-linearity in both topological structure and nodal attributes through graph convolutional autoencoder, (b) fully exploits the intrinsic information of the network with the description of various proximities, (c) and preserve the differences between anomalies and the majority by applying Laplacian sharpening. We perform anomaly detection by measuring the reconstruction errors of nodes. Experimental results on realworld datasets demonstrate that DeepAE outperforms the stateof-art baselines.

In the field of remote surveillance, acquiring the high-quality voice of target has always been an exciting goal. In this paper, we propose a method based on convolutional neural network to extract the target’s speech signals remotely. The method consists of two parts: the optical setup enables us to obtain speckle images conveniently and covertly, and the convolutional neural model is used to recover speech signals from continuous speckle images. Correlation coefficient and root mean square error metrics show the effectiveness of our method for high-quality speech extraction. Compared to the traditional spatial image correlation, our convolutional neural model is more accurate and more efficient in speckle image processing. The model gets an average accuracy of 94% on real data and 98% on simulated data, which is far better than the spatial image correlation. Besides, by using GPU hardware, the model can process speckle images up to 237 frames per second, far more than 10 frames per second of the spatial image correlation. Experimental results show that the method is simple, efficient and accurate, which proves our significant progress in the field of remote sound extraction.

Nowadays, increasing Android applications attempt to obtain a large number of sensitive user information such as Contacts, SMS, Call logs, IMEI, IMSI without rational necessity, which has seriously threatened the privacy of users. However, the existing Android cannot effectively prevent the above risks. To solve this problem, this paper proposes a novel, user-driven sensitive information management model-UIDroid. UIDroid redefines the subject, object, definition of security level, legitimacy of operations, and system security status. With UIDroid, users could authorize the sub-functions of an application to access sensitive information with rational security levels based on essential requirements on the accuracy of the sensitive data. The prototype of UIDroid is developed to verify the feasibility of the UIDroid and compatibility with existing applications. Extensive experiments show that UIDroid can effectively prevent malicious applications from getting unnecessary sensitive user information with unnecessary accuracy. Meanwhile, the overall performance overhead introduced by UIDroid is less than 4.8%.

Practical Byzantine Fault Tolerance (PBFT) is an optional consensus protocol for consortium blockchains scenarios where strong consistency is required. However, it also inevitably incurs high energy consumption, low efficiency and poor scalability. What is more, the reliability of the consensus node cannot be guaranteed by itself. For addressing these problems, this paper proposes practical byzantine consensus algorithm based on quantified-role (QPBFT), which can achieve the following advantages: (1) Improving the security and reliability of the blockchain. The reliability attributes of nodes are quantified based on analytic hierarchy process (AHP), those nodes with high reliability evaluation scores are more likely to participate in block production by introduction of the quantified-role, which can ensure the reliability of blockchain network; (2) Realizing high efficiency and low energy consumption. Voting mechanism is adopted to simplify and optimize the PBFT consensus process; (3) Implementing adaptation to dynamic network environments. Management nodes, voting nodes, candidate nodes, and ordinary nodes are dynamically adjusted according to node reliability evaluation score for optimizing consensus performance. The paper demonstrates the security feature including reliability and fault tolerance. Meanwhile, simulation experiments are conducted to validate the higher efficiency and less resource consumption of QPBFT compared with PBFT.

Anomaly Detection in Dynamic Networks plays a critical role in various real-world applications such as cyberse-curity, e-commerce, and social media. Recent approaches based on graph neural networks have achieved fruitful results in static networks, and most of the researches focus on learning node embeddings to represent the large-scale complex networks, thereby facilitating downstream anomaly detection task. However, these methods require the whole network to extract intrinsic properties, so they are sensitive to the frequent changes of nodes and incapable of capturing the dynamism as realworld networks evolve over time. In this paper, we propose a novel framework DynAD for anomalous edge detection on time-evolving networks, which performs adaptive parameter learning in an end-to-end manner. In particular, DynAD first extracts fixed-size node embedding from each snapshot with temporal graph convolution and pooling operations. Then, it captures the temporal information of the graph sequence using Gated recurrent units (GRU) for anomaly detection, where an attention mechanism is employed to highlight the differences between the dynamic patterns. Experimental results on three real-world datasets illustrate that DynAD significantly outperforms the state-of-the-art baseline methods in anomaly detection.

Previous works have designed many deep learning models for Android malware detection using various features (e.g. permissions, APIs et.) to achieve better classification performance. However, these methods usually input each feature into the classifier independently and completely (using One-Hot Encoding) so that features are orthogonal to each other. This discrete representation is difficult to preserve the semantic information of features. In this paper, we design two feature segmentation methods to enhance the semantics of the features in preprocessing. Besides that, we propose a malware detection model that consists of a distributed representation process for Android features and an optimized convolutional neural network for classification, named Semantic Analysis Detection (SADroid). In SADroid, the distance between features with similar semantics is closer in vector space. It provides the semantic information of features to the classifier to improve the classification performance. In the evaluation, SADroid outperforms the advanced models in detection accuracy on a data set of 19,600 applications, while maintaining a low computational cost.

6G is expected to support the unprecedented Internet of everything scenarios with extremely diverse and challenging requirements. To fulfill such diverse requirements efficiently, 6G is envisioned to be space-aerial-terrestrial-ocean integrated three-dimension networks with different types of slices enabled by new technologies and paradigms to make the system more intelligent and flexible. As 6G networks are increasingly complex, heterogeneous and dynamic, it is very challenging to achieve efficient resource utilization , seamless user experience , automatic management and orchestration. With the advancement of big data processing technology, computing power and the availability of rich data, it is natural to tackle complex 6G network issues by leveraging artificial intelligence (AI). In this paper, we make a comprehensive survey about AI-empowered networks evolving towards 6G. We first present the vision of AI-enabled 6G system, the driving forces of introducing AI into 6G and the state of the art in machine learning . Then applying machine learning techniques to major 6G network issues including advanced radio interface , intelligent traffic control, security protection, management and orchestration, and network optimization is extensively discussed. Moreover, the latest progress of major standardization initiatives and industry research programs on applying machine learning to mobile networks evolving towards 6G are reviewed. Finally, we identify important open issues to inspire further studies towards an intelligent, efficient and secure 6G system.

Traditional Android malware detection based on static analysis are experience-driven rule writing and feature engineering methods. Such methods only analyze the combination relationship or weight between rules and features of malwares, both of which lack deep representations of the semantics. In this paper, the problem of Android malware detection is considered as task of text categorization, thus we propose FSNet, an effective and efficient data-driven model to solve this problem. FSNet has been designed to learn complex implicit semantic representations from data composed of a single-feature source. In addition, a new method of feature segmentation is proposed to further improve the performance of the model. Extensive experiments have been conducted. In an evaluation with two large datasets with about 16,000 applications, FSNet shows its remarkable superiority over the traditional methods and outperforms the state-of-the-art model at a fraction of the computational cost.

With the wide application of MIMO-OFDM technology, Channel State Information (CSI) as a fine-grained feature can be extracted from PHY layer with Wi-Fi. Although CSI has a better performance on expressing the spatial and temporal features of wireless signal, it is more sensitive to the multipath reflection. As a result, Line-of-Sight (LoS) identification and corresponding subcarrier parameter estimation play an important role in improving positioning accuracy. In this paper, we propose a complete parameter processing framework, which involves phase calibration, phase ambiguity elimination, subcarrier parameter (amplitude and phase) estimation of LoS, fingerprint feature extraction and relationship mapping from fingerprint feature to position estimate. The experimental results show that, compared with existing algorithm, our proposed algorithm improves the positioning accuracy by 2.3% in LoS and 10.7% in NLoS cases.

While recent works have shown that deep learning method can improve the malware classification accuracy, the lack of the transparency has restricted its application in anti-virus scan engines. Existing researches have attempted to provide solutions to give high-fidelity explanations of the model's decision. However, current methods are not optimized for application security task, leading to a poor performance in Android malware detection. In this paper, we propose a backtracking method to infer suspicious features of the apps to explain the reason of classification. Besides, we also propose a malware detection model based on the fusion convolutional neural network using different types of features (e.g., permission, API, URL, etc.). For maximizing the benefits of encompassing multiple feature types, our framework trains the sub-models for each type of features separately and merges them at the end of the system to obtain a comprehensive classification result. The experimental results show that the backtracking method has a significant improvement in fidelity level compared with existing methods. Furthermore, we evaluate the performance of the proposed framework with other existing works. Leveraging the backtracking method, our framework has better performance in classification and significantly reduces detection time by 69% compared with prior approaches.

Various research works have been proposed for Wi-Fi-based indoor localization, including Received Signal Strength Indicator (RSSI)-based fingerprint algorithm, Angle of Arrival (AoA)-based algorithm and so on. However, since RSSI value cannot accurately express the spatial features of emitted wireless signal, and the interfering noise in indoor environment makes the wireless signal distortion, RSSI-based localization algorithm cannot achieve an ideal accuracy. In this paper, we utilize Channel State Information (CSI) extracted from MIMO-OFDM PHY layer as fingerprint image to express the spatial and temporal features of Wi-Fi signal. At the same time, an indoor localization algorithm is also proposed, which is based on convolutional neural network and dual-factor enhanced variational Bayes adaptive Kalman filter, to achieve accurate position estimate with time-varying measurement noise and process noise in complex indoor environment. According to the simulation results, compared with existing methods, our proposed algorithm improves the positioning accuracy up to 51.8%. In the real indoor environment, our proposed algorithm improves the positioning accuracy up to 22% in LoS scenario, and 9.8% in NLoS scenario, respectively.

At present, there has been a booming interest in utilizing Channel State Information (CSI) extracted from MIMO-OFDM PHY layer to achieve precise indoor localization. Compared with Received Signal Strength Indicator (RSSI), CSI as a fine-grained feature has a better performance on expressing the spatial and temporal features of wireless signal. As a result, CSI is more sensitive to the noise interference and multi-path. In this paper, we present a direct-path based fingerprint extraction algorithm for indoor localization in noisy and multi-path indoor environment. Our proposed algorithm firstly extracts the amplitude and phase measurements of direct-path from the raw CSI, and then calculates the unique fingerprint feature according to the filtered CSI. The experimental results show that our proposed algorithm improves the positioning accuracy up to 23.5% in complex indoor multipath environment.

Radio Frequency Identification (RFID)-based fingerprint indoor positioning and tracking technology is one of the key technologies in the study of wireless sensor network, and has been widely used in noisy environment. However, due to the time and space fluctuation in Received Signal Strength Indicator (RSSI) of RFID, indoor positioning accuracy is not satisfactory. In this work, we present a Multi-Direction Weight Position Kalman Filter (MDWPKF) according to the spacial feature of RSSI. This algorithm combines the Multi-Direction data collection method, with Standard Kalman Filter and fingerprint matching algorithm to achieve the signal fluctuation reduction, noise removal and 2D fingerprint mapping. At the same time, the Improved Position Kalman Filter (IPKF) in our proposed MDWPKF takes the advantages of Gaussian weight computation and velocity estimator to refine the position and velocity estimates. Compared with traditional PKF, the MDWPKF improves the positioning accuracy by 17.7%, and the velocity accuracy by 10.2%. Compared with Fingerprint Kalman Filter (FKF), the MDWPKF can be used for the tracking of both moving target (including position and velocity estimates) and stationary object.

With the rapid development of the Internet of Things, location information becomes increasingly important for various applications. However, the localization information of network devices is vulnerable to various attacks and not always trustworthy. In this paper, we propose a location verification scheme that allows the access point (AP) to verify credibility of a reported location from a network node with assistance of an obstacle that moves actively in the network at a random speed. When the obstacle blocks the transmissions between the AP and a network node, the received signal strength (RSS) at the node is reduced. For location verification, a network node is asked to report its location and the RSS for a period of time. Based on the changes in the reported RSS and the mobility information of the obstacle, the AP can determine whether the network node has reported the correct location. An analytical model is developed to find the performance of the proposed scheme. Simulation results show that the proposed scheme achieves high probability of detecting malicious nodes and low probability of treating legitimate nodes as malicious. Simulation results have also verified the accuracy of the analysis.

We build an ubiquitous abnormal activity detection system, namely NotiFi, for accurately detecting the abnormal activities on commercial off-the-shelf (COTS) IEEE 802.11 devices. In contrast to the traditional wearable sensor based and computer vision based systems which require additional sensors or enough lighting in line-of-sight (LoS) scenario, we proceed directly with abnormal activity characterization and activity modeling at the WiFi signal level based on Channel State Information (CSI). The intuition of NotiFi is that whenever the human body occludes the wireless signal transmitting from the access point to the receiver, the phase and the amplitude information of Channel State Information (CSI) will change sensitively. By creating a multiple hierarchical Dirichlet processes, NotiFi automatically learns the number of human body activity categories for abnormal detection. Experimental results in three typical indoor environments indicate that NotiFi can achieve satisfactory performance in accuracy, robustness and stability.

The open nature of Android allows application developers to take full advantage of the system. While the flexibility is brought to developers and users, it may raise significant issues related to malicious applications. Traditional malware detection approaches based on signatures or abnormal behaviors are invalid when dealing with novel malware. To solve the problem, machine learning algorithms are used to learn the distinctions between malware and benign apps automatically. Deep learning, as a new area of machine learning, is developing rapidly as its better characterization of samples. We thus propose DeepFlow, a novel deep learning-based approach for identifying malware directly from the data flows in the Android application. We test DeepFlow on thousands of benignware and malware. The results show that DeepFlow can achieve a high detection F1 score of 95.05%, outperforming traditional machine learning-based approaches, which reveals the advantage of deep learning technique in malware detection.

The number of network intrusions, such as large-scale stealthy scans, worms, and distributed denial-of-service (DDoS) attacks, has significantly increased. Collaborative intrusion detection system (CIDS) becomes an essential part for analyzing multiple network security simultaneously. The trust-based packet filter method using Bayesian inference tries to decrease the processing burden, but overhead network packets make that performance and accuracy are still open issues. In this paper, we propose an Opportunistic Probe model, which is a transport entity that carries encrypted characteristic attributes from trusted host to the checking host. A Detection Time Optimization Algorithm is proposed to determine the trusted period of hosts during which the unnecessary detection can be reduced. The case study and experimental analysis demonstrates the effectiveness, scalability and robustness of the proposed approach.

Content Centric Mobile Ad-hoc NETwork (CCMANET) applies the advantages of Content Centric networking (CCN) into Mobile Ad Hoc Network(MANET) to overcome the drawbacks of low efficiency and unstable in transmission. Caching scheme is one of the key components of CCMANET. However, the caching scheme in CCMANET has not been well explored. In this paper, a novel cooperative caching scheme based on generalized dominating set and local content popularity for CCMANET is proposed. First, a virtual backbone in CCMANET is constructed by generalized dominating set to make the arbitrary topology become two-level hierarchy and a collaborative cache placement scheme between the two hierarchies is designed. Second, we propose a method of computing the local content popularity and a cache replacement scheme based on the local content popularity. Simulation results show that the proposed caching scheme can effectively reduces both path stretch value and server load, and improves the hit ratio compared with the existing caching schemes.

In LTE system, HTTP streaming services sometimes experience video quality deterioration because of the constraint of available wireless resources, which leads to reduce of Quality of Experience (QoE). In this paper, we propose a new scheduling scheme which is QoE-oriented from user's perceptive to improve the performance of HTTP streaming service in a LTE system. First of all, we adopt the jerkiness, frame freezing for example, perceived at an end user as the prominent QoE factor and implement a jerkiness measuring algorithm on end devices. Secondly, we implement a prioritized traffic flow scheduling algorithm at the base station, and put the end users who experience the maximum jerkiness to be scheduled with the highest priority. Finally, we compare the performance of the proposed QoE-oriented scheme with the traditional scheduling algorithm (i.e. Round Robin scheduling algorithm) in terms of jerkiness for HTTP streaming service. Simulation result shows that the proposed scheme can dramatically improve QoE from user's perspective by effectively decrease the jerkiness of HTTP streaming video.

Problem to real time detect existence of cell phones stay in power on state in a given area is a technology challenge because most time cell phones keep radio silence on a standby mode. This paper proposed two solutions, "virtual base station solution" and "ready beacon utilization solution" to solve this problem. Location updating registration of a cell phone entering into a new registration area is made use of to fulfill a lure technology and the problem of cell phones detection is settled perfectly.