Biblio

Knowledge Graph can describe the concepts in the objective world and the relationships between these concepts in a structured way, and identify, discover and infer the relationships between things and concepts. It has been developed in the field of medical and health care. In this paper, the method of natural language processing has been used to build chronic disease knowledge graph, such as named entity recognition, relationship extraction. This method is beneficial to forecast analysis of chronic disease, network monitoring, basic education, etc. The research of this paper can greatly help medical experts in the treatment of chronic disease treatment, and assist primary clinicians with making more scientific decision, and can help Patients with chronic diseases to improve medical efficiency. In the end, it also has practical significance for clinical scientific research of chronic disease.

With the rapid growth of online services, the number of online accounts proliferates. The security of a single user account no longer depends merely on its own service provider but also the accounts on other service platforms (We refer to this online account environment as Online Account Ecosystem). In this paper, we first uncover the vulnerability of Online Account Ecosystem, which stems from the defective multi-factor authentication (MFA), specifically the ones with SMS-based verification, and dependencies among accounts on different platforms. We propose Chain Reaction Attack that exploits the weakest point in Online Account Ecosystem and can ultimately compromise the most secure platform. Furthermore, we design and implement ActFort, a systematic approach to detect the vulnerability of Online Account Ecosystem by analyzing the authentication credential factors and sensitive personal information as well as evaluating the dependency relationships among online accounts. We evaluate our system on hundreds of representative online services listed in Alexa in diversified fields. Based on the analysis from ActFort, we provide several pragmatic insights into the current Online Account Ecosystem and propose several feasible countermeasures including the online account exposed information protection mechanism and the built-in authentication to fortify the security of Online Account Ecosystem.

Arbitrary style transfer refers to generate a new image based on any set of existing images. Meanwhile, the generated image retains the content structure of one and the style pattern of another. In terms of content retention and style transfer, the recent arbitrary style transfer algorithms normally perform well in one, but it is difficult to find a trade-off between the two. In this paper, we propose the Deep Content Guidance Network (DCGN) which is stacked by content guidance (CG) layers. And each CG layer involves one position self-attention (pSA) module, one channel self-attention (cSA) module and one content guidance attention (cGA) module. Specially, the pSA module extracts more effective content information on the spatial layout of content images and the cSA module makes the style representation of style images in the channel dimension richer. And in the non-local view, the cGA module utilizes content information to guide the distribution of style features, which obtains a more detailed style expression. Moreover, we introduce a new permutation loss to generalize feature expression, so as to obtain abundant feature expressions while maintaining content structure. Qualitative and quantitative experiments verify that our approach can transform into better stylized images than the state-of-the-art methods.

The goal of neural style transfer is to transform images by the deep learning method, such as changing oil paintings into sketch-style images. The Generative Adversarial Network (GAN) has made remarkable achievements in neural style transfer in recent years. At first, this paper introduces three typical neural style transfer methods, including StyleGAN, StarGAN, and Transparent Latent GAN (TL-GAN). Then, we discuss the advantages and disadvantages of these models, including the quality of the feature axis, the scale, and the model's interpretability. In addition, as the core of this paper, we put forward innovative improvements to the above models, including how to fully exploit the advantages of the above three models to derive a better style conversion model.

Mounting concerns about safety and security have resulted in an intricate ecosystem of guidelines, compliance measures, directives and policy reports for cybersecurity of all critical infrastructure. By definition, such guidelines and policies are written in linear sequential text form that makes them difficult to integrate, or to understand the policy-technology-security interactions, thus limiting their relevance for science of security. We propose to develop text-to-analytics methods and tools focusing on CPS domains such as smart grids

To improve the security and reliability of the system in case of sensor failure, a fault diagnosis algorithm based on neural network is proposed to locate the fault quickly and reconstruct the control system in this paper. Firstly, the typical airborne sensors are introduced and their common failure modes are analyzed. Then, a new method of complex feature extraction using wavelet packet is put forward to extract the fault characteristics of UAV sensors. Finally, the observer method based on BP neural network is adopted to train and acquire data offline, and to detect and process single or multiple sensor faults online. Matlab simulation results show that the algorithm has good diagnostic accuracy and strong generalization ability, which also has certain practicability in engineering.

In the multivariable fault diagnosis of industrial process, due to the existence of correlation between variables, the result of fault diagnosis will inevitably appear "smearing" effect. Although the fault diagnosis method based on the contribution of multi-dimensional reconstruction is helpful when multiple faults occur. But in order to correctly isolate all the fault variables, this method will become very inefficient due to the combination of variables. In this paper, a fault diagnosis method based on kNN and MRBC is proposed to fundamentally avoid the corresponding influence of "smearing", and a fast variable selection strategy is designed to accelerate the process of fault isolation. Finally, simulation study on a benchmark process verifies the effectiveness of the method, in comparison with the traditional method represented by FDA-based method.

Wireless relay network is a solution for transmitting information from a source node to a sink node far away by installing a relay in between. The broadcasting nature of wireless communication allows the sink node to receive part of the data sent by the source node. In this way, the relay does not need to receive the whole piece of data from the source node and it does not need to forward everything it received. In this paper, we consider the application of batched network coding, a practical form of random linear network coding, for a better utilization of such a network. The amount of innovative information at the relay which is not yet received by the sink node, called the innovative rank, plays a crucial role in various applications including the design of the transmission scheme and the analysis of the throughput. We present a visualization of the innovative rank which allows us to understand and derive formulae related to the innovative rank with ease.

With the ubiquitous network applications and the continuous development of network attack technology, all social circles have paid close attention to the cyberspace security. Intrusion detection systems (IDS) plays a very important role in ensuring computer and communication systems security. Recently, deep learning has achieved a great success in the field of intrusion detection. However, the high computational complexity poses a major hurdle for the practical deployment of DL-based models. In this paper, we propose a novel approach based on a lightweight deep neural network (LNN) for IDS. We design a lightweight unit that can fully extract data features while reducing the computational burden by expanding and compressing feature maps. In addition, we use inverse residual structure and channel shuffle operation to achieve more effective training. Experiment results show that our proposed model for intrusion detection not only reduces the computational cost by 61.99% and the model size by 58.84%, but also achieves satisfactory accuracy and detection rate.

To improve the safety precaution level of network system, a combined network intrusion detection method is proposed based on Supervised Locality Preserving Projections (SLPP) feature extraction and Extreme Learning Machine (ELM). In this method, the feature extraction capability of SLPP is first used to reduce the dimensionality of the original network connection and system audit data, and get a feature set, then, based on this, the advantages of ELM in pattern recognition is adopted to build a network intrusion detection model for detecting and determining intrusion behavior. Simulation results show that, under the same experiment conditions, compared with traditional neural networks and support vector machines, the proposed method has more advantages in training efficiency and generalization performance.

This work seeks to advance the state of the art in HPC I/O performance analysis and interpretation. In particular, we demonstrate effective techniques to: (1) model output performance in the presence of I/O interference from production loads; (2) build features from write patterns and key parameters of the system architecture and configurations; (3) employ suitable machine learning algorithms to improve model accuracy. We train models with five popular regression algorithms and conduct experiments on two distinct production HPC platforms. We find that the lasso and random forest models predict output performance with high accuracy on both of the target systems. We also explore use of the models to guide adaptation in I/O middleware systems, and show potential for improvements of at least 15% from model-guided adaptation on 70% of samples, and improvements up to 10 x on some samples for both of the target systems.

With the development of communication technology, the disadvantages of traditional notification methods such as low efficiency gradually appear. With the introduction of WAP with WTLS security and its development and maintenance, more and more notification systems are using this technology. Through the analysis, design and implementation of notification system for large user groups, this paper studies how to collect and notify data without affecting the business system, and proposes a scheme of real-time data acquisition and filtering based on trigger. The middleware and application server implementation transaction management and database operation to separate CICS middleware technology based on research using UNIXC, Socket programming, SQL statements, SYBASE database technology, from the system requirements, business process, function structure, database and data structure, the input and output of the system, system testing the aspects such as design of practical significance to intelligent notification system for large user groups. Finally, the paper describes the test effect of the system in detail. 10 users send 1, 5, 10 and 20 strokes at the same time, and the completion time is 0.28, 1.09, 1.58 and 2.20 seconds, which proves that the system has practical significance.

In recent years, the commodities industry has grown rapidly under the stimulus of domestic demand and the expansion of cross-border trade. It has also been combined with the rapid development of e-commerce technology in the same period to form a flexible and efficient e-commerce system for bulk commodities. However, the hasty combination of both has inspired a lack of effective regulatory measures in the bulk industry, leading to constant industry chaos. Among them, the problem of lagging evidence in regulatory platforms is particularly prominent. Based on this, we design a blockchain-based evidential and secure bulk-commodity supervisory system (abbr. BeBus). Setting different privacy protection policies for each participant in the system, the solution ensures effective forensics and tamper-proof evidence to meet the needs of the bulk business scenario.

The digital transformation is injecting energy into economic growth and governance improvement for the China government. Digital governance and e-government services are playing a more and more important role in public management and social governance. Meanwhile, cyber-attacks and threats become the major challenges for e-government application systems. In this paper, we proposed a novel dynamic access entry scheme for web application, which provide a rapidly-changing defender-controlled attack surface based on Moving Target Defense (MTD) technology. The scheme can turn the static keywords of Uniform Resource Locator (URL) into the dynamic and random ones, which significantly increase the cost to adversaries attack. We present the prototype of the proposed scheme and evaluate the feasibility and effectiveness. The experimental results demonstrated the scheme is practical and effective.

Advanced persistent threat (APT) attackers usually conduct a large number of network reconnaissance before a formal attack to discover exploitable vulnerabilities in the target network and system. The static configuration in traditional network systems provides a great advantage for adversaries to find network targets and launch attacks. To reduce the effectiveness of adversaries' continuous reconnaissance attacks, this paper develops a moving target defense (MTD) enhanced cyber deception defense system based on software-defined networks (SDN). The system uses virtual network topology to confuse the target network and system information collected by adversaries. Also Besides, it uses IP address randomization to increase the dynamics of network deception to enhance its defense effectiveness. Finally, we implemented the system prototype and evaluated it. In a configuration where the virtual network topology scale is three network segments, and the address conversion cycle is 30 seconds, this system delayed the adversaries' discovery of vulnerable hosts by an average of seven times, reducing the probability of adversaries successfully attacking vulnerable hosts by 83%. At the same time, the increased system overhead is basically within 10%.

In order to suppress the spread of zero-day virus in the network effectively, a zero-day virus suppression strategy was proposed. Based on the mechanism of zero-day virus transmission and the idea of platform dynamic defense, the corresponding methods of virus transmission suppression are put forward. By changing the platform switching frequency, the scale of zero-day virus transmission and its inhibition effect are simulated in a small-world network model. Theory and computer simulation results show that the idea of platform switching can effectively restrain the spread of virus.

As Internet of Things(IOT) devices become intelli-gent, more powerful computing capability is required. Multi-core processors are widely used in IoT devices because they provide more powerful computing capability while ensuring low power consumption. Therefore, it requires the operating system on IoT devices to support and optimize the scheduling algorithm for multi-core processors. Nowadays, microkernel-based operating systems, such as QNX Neutrino RTOS and HUAWEI Harmony OS, are widely used in IoT devices because of their real-time and security feature. However, research on multi-core scheduling for microkernel operating systems is relatively limited, especially for load balancing mechanisms. Related research is still mainly focused on the traditional monolithic operating systems, such as Linux. Therefore, this paper proposes a low-latency, high- performance, and high real-time centralized global dynamic multi-core load balancing method for the microkernel operating system. It has been implemented and tested on our own microkernel operating system named Mginkgo. The test results show that when there is load imbalance in the system, load balancing can be performed automatically so that all processors in the system can try to achieve the maximum throughput and resource utilization. And the latency brought by load balancing to the system is very low, about 4882 cycles (about 6.164us) triggered by new task creation and about 6596 cycles (about 8.328us) triggered by timing. In addition, we also tested the improvement of system throughput and CPU utilization. The results show that load balancing can improve the CPU utilization by 20% under the preset case, while the CPU utilization occupied by load balancing is negligibly low, about 0.0082%.

In order to meet the actual needs of operating system localization and high-security operating system, this paper proposes a multi-core embedded high-security operating system inter-core communication mechanism centered on private memory on the core based on the cache mechanism of DSP processors such as Feiteng design. In order to apply it to the multi-core embedded high-security operating system, this paper also combines the priority scheduling scheme used in the design of our actual operating system to analyze the certainty of inter-core communication. The analysis result is: under this communication mechanism There is an upper limit for end-to-end delay, so the certainty of the communication mechanism is guaranteed and can be applied to multi-core high-security embedded operating systems.

Online social network (OSN) is an ideal venue to enhance one's visibility. This paper considers how a user (called requester) in an OSN selects a small number of available users and invites them as new friends/followers so as to maximize his "social visibility". More importantly, the requester has to do this under the anonymity setting, which means he is not allowed to know the neighborhood information of these available users in the OSN. In this paper, we first develop a mathematical model to quantify the social visibility and formulate the problem of visibility maximization with anonymity guarantee, abbreviated as "VisMAX-A". Then we design an algorithmic framework named as "AdaExp", which adaptively expands the requester's visibility in multiple rounds. In each round of the expansion, AdaExp uses a query oracle with anonymity guarantee to select only one available user. By using probabilistic data structures like the k-minimum values (KMV) sketch, we design an efficient query oracle with anonymity guarantees. We also conduct experiments on real-world social networks and validate the effectiveness of our algorithms.

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party data (e.g., data from the Internet or third-party data company). This raises the question of whether adopting untrusted third-party data can pose a security threat. In this paper, we demonstrate that it is possible to inject the hidden backdoor for infecting speaker verification models by poisoning the training data. Specifically, we design a clustering-based attack scheme where poisoned samples from different clusters will contain different triggers (i.e., pre-defined utterances), based on our understanding of verification tasks. The infected models behave normally on benign samples, while attacker-specified unenrolled triggers will successfully pass the verification even if the attacker has no information about the enrolled speaker. We also demonstrate that existing back-door attacks cannot be directly adopted in attacking speaker verification. Our approach not only provides a new perspective for designing novel attacks, but also serves as a strong baseline for improving the robustness of verification methods. The code for reproducing main results is available at https://github.com/zhaitongqing233/Backdoor-attack-against-speaker-verification.

In machine learning Trojan attacks, an adversary trains a corrupted model that obtains good performance on normal data but behaves maliciously on data samples with certain trigger patterns. Several approaches have been proposed to detect such attacks, but they make undesirable assumptions about the attack strategies or require direct access to the trained models, which restricts their utility in practice.This paper addresses these challenges by introducing a Meta Neural Trojan Detection (MNTD) pipeline that does not make assumptions on the attack strategies and only needs black-box access to models. The strategy is to train a meta-classifier that predicts whether a given target model is Trojaned. To train the meta-model without knowledge of the attack strategy, we introduce a technique called jumbo learning that samples a set of Trojaned models following a general distribution. We then dynamically optimize a query set together with the meta-classifier to distinguish between Trojaned and benign models.We evaluate MNTD with experiments on vision, speech, tabular data and natural language text datasets, and against different Trojan attacks such as data poisoning attack, model manipulation attack, and latent attack. We show that MNTD achieves 97% detection AUC score and significantly outperforms existing detection approaches. In addition, MNTD generalizes well and achieves high detection performance against unforeseen attacks. We also propose a robust MNTD pipeline which achieves around 90% detection AUC even when the attacker aims to evade the detection with full knowledge of the system.

Three issues should be addressed in ubiquitous power Internet of things (IoT) terminals, such as lack of terminal standardization, high business coupling and weak local intelligent processing ability. The application of operating system in power IoT terminals provides the possibility to solve the above problems, but needs to address the real-time and security problems. In this paper, TrustZone based virtualization architecture is used to tackle the above real-time and security problems, which adopts the dual system architecture of real-time operating system (FreeRTOS) to run real-time tasks, such as power parameter acquisition and control on the real-time operating system, to solve the real-time problem; And non real-time tasks are run on the general operating system(Linux) to solve the expansibility problem of power terminals with hardware assisted virtualization technology achieving the isolation of resources, ensuring the safety of power related applications. The scheme is verified on the physical platform. The results show that the dual operating system power IoT terminal scheme based on ARM TrustZone meets the security requirements and has better real-time performance, with unifying terminal standards, business decoupling and enhancing local processing capacity.

Usually on the top of Smart Chip covered with active shielding layer to prevent invasive physical exploration tampering attacks on part of the chip's function modules, to obtain the chip's critical storage data and sensitive information. This paper introduces a design based on UMC55 technology, and applied to the safety chip active shielding layer method for layout design, the layout design from the two aspects of the metal shielding line and shielding layer detecting circuit, using the minimum size advantage and layout design process when the depth of hidden shielding line interface and port order connection method and greatly increased the difficulty of physical attack. The layout design can withstand most of the current FIB physical attack technology, and has been applied to the actual smart card design, and it has important practical significance for the security design and attack of the chip.

Major manufacturers and retailers are increasingly using RFID systems in supply-chain scenarios, where theft of goods during transport typically causes significant economic losses for the consumer. Recent sample-based authentication methods attempt to use a small set of random sample tags to authenticate the integrity of the entire tag population, which significantly reduces the authentication time at the expense of slightly reduced reliability. The problem is that it still incurs extensive initialization overhead when writing the authentication information to all of the tags. This paper presents KTAuth, a lightweight integrity authentication approach to efficiently and reliably detect missing tags and counterfeit tags caused by stolen attacks. The competitive advantage of KTAuth is that it only requires writing the authentication information to a small set of deterministic key tags, offering a significant reduction in initialization costs. In addition, KTAuth strictly follows the C1G2 specifications and thus can be deployed on Commercial-Off-The-Shelf RFID systems. Furthermore, KTAuth proposes a novel authentication chain mechanism to verify the integrity of tags exclusively based on data stored on them. To evaluate the feasibility and deployability of KTAuth, we implemented a small-scale prototype system using mainstream RFID devices. Using the parameters achieved from the real experiments, we also conducted extensive simulations to evaluate the performance of KTAuth in large-scale RFID systems.

Return-oriented programming(ROP) is a prevalent technique that targets return addresses to hijack control flow. To prevent such attack, researchers mainly focus on either Shadow Stack or MAC-based mechanisms(message code authentication). But Shadow Stack suffers from additional memory overhead and information leakage, while MAC-based mechanisms(e.g. Zipper Stack) impose high runtime overhead for MAC calculations.In this paper, we propose Twine Stack, a hybrid and efficient return address protection mechanism with lightweight hardware extension. It utilizes a tiny hardware shadow stack to realize a new multi-chain Zipper Stack. Specifically, each entry in the shadow stack stores a return address and its MAC in each chain, allowing queueing calculation with just one hash module. At meantime, some return address verifications could be done by comparison with the hardware shadow stack, instead of calculation again. We implemented Twine Stack on RISC-V architecture, and evaluated it on FPGA board. Our experiments show that Twine Stack reduces over 95% hash verifications, and imposes merely 1.38% performance overhead with an area overhead of 974 LUTs and 726 flip flops. The result demonstrates that our hybrid scheme mitigates the drawbacks of each separate scheme.