Due to its exceptional performance and memory security, Java is extensively employed in enterprise applications, thereby rendering any vulnerability in Java applications capable of causing significant repercussions. In recent years, due to the frequent occurrence of network attacks, new attack methods continue to emerge while software systems become increasingly intricate and unstable under the weight of historical burdens. Consequently, static analysis techniques are imperative for identifying security risks in code during the coding phase. The prevailing approach in static analysis involves transforming code into a standardized intermediate representation and conducting vulnerability detection, without code execution. However, this methodology often yields detection results accompanied by a considerable false positive rate. We propose VulnSlicer, a tool based on graph similarity matching and vulnerability subgraph slice technology. This tool not only enables efficient vulnerability retrieval but also effectively reduces the false positive rate by leveraging the slice mechanism to save historical vulnerabilities. Additionally, it facilitates rapid matching of accumulated vulnerabilities in the database and further mitigates false positives through the introduction of a keyframe mechanism. In the experiment, we conducted a comparative analysis of several existing static detection tools to assess their effectiveness in detecting vulnerabilities within the same codebase. Experiments show that VulnSlicer has decent accuracy and lower false positive rate.
this paper proposed a cross-chain multi-dimensional reputation model based on block-chain to deal with the nodes’ risk assessment in block-chain. When the nodes joined the network, the block-chain was difficult to evaluate these nodes’ behavioral changes especially those happened in recent time. This model comprehensively took the individual behavior and transaction history of enterprise nodes, and adjusted the reputation value of the initial node dynamically by means of the recommendation code. Meanwhile, the reputation model has been brought in a liability sharing mechanism to construct a multi-level and dynamic reputation evaluation mechanism. At same time, the quantum random number could be used in this model to distinguish the malicious nodes from the honest ones. Finally, the test of the improved multi-dimensional reputation model scheme was implemented on the Fabric simulation system. The experimental results show that this model could effectively identify the possible deception behavior of nodes after joining the block-chain, improve the overall security and the success rate of transactions, enhance the users’ trust.
Elastic ring (ER) is widely adopted for its compact size and ease of assembly and have become a prevalent type of elastic support within rotor-support systems. However, it may exhibit stiffness nonlinearity under specific operating conditions, potentially compromising the safety of the rotor system. This paper examines the influence of elastic ring stiffness on the critical speed of a specific aero-engine rotor support structure, focusing on related nonlinear phenomena. The Levenberg-Marquardt method was employed to optimize key parameters, including the stiffness and clearance of the elastic ring, with the second-order critical speed as the optimization goal. Finite element analysis was performed to validate the optimization results, which were found to be both effective and practically applicable. The finding provides a significant reference for the design and analysis of aero-engine rotor systems and similar applications.
BGP route leak represents a significant vulnerability in BGP security. The occurrence of BGP route leak can lead to increased internet latency and diminished service quality in less severe cases, and in more severe instances, it can result in large-scale regional outages or substantial traffic redirection, causing considerable financial losses to network operators and users. Thus, the ability to accurately and promptly identify route leak is of paramount importance for maintaining internet security. Current route leak detection methods typically involve a trade-off between accuracy and real-time performance, making it challenging to achieve both simultaneously. To address this issue, this paper proposes the Leak-Detector framework, which synthesizes the strengths of existing advanced methodologies. By integrating AS hegemony indicators with machine learning models, Leak-Detector provides accurate and real-time detection of route leak incidents, and it can precisely report both the suspects and the timing of the leak. Application of Leak-Detector to real-world route leak detection demonstrates that it achieves an accuracy of 85%, recall of 84%, and F1 score of 83%, with minimal detection latency. Furthermore, it accurately identifies most route leak suspects and their occurrence times.
In recent years, learning based methods are introduced to identify the elements in the point cloud, which are easily captured with UAV and LiDAR. However, supervised learning needs great efforts in data labeling, and cannot well adapt to the point clouds in different places. In this paper, we propose an unsupervised point cloud segmentation method that can can distinguish identical elements from the point cloud. Firstly, with the collected point cloud, pre-processing including denoising and downsampling is conducted. After that, cloud elements such as transmission lines, towers, buildings, roads and vegetation are extracted with unsupervised algorithms including DBSCAN, and other point cloud processing algorithms such as cloth filtering and PCA. To be specific, intrinsic features, e.g., the evaluation, the density, the curvature, of the point clouds are used in the unsupervised learning and clustering. Finally, with the safety distance rules, potential danger points that locate close to the transmission lines are detected, and a danger point report is further generated. In addition, based on the algorithm, a point analysis and management system is developed. With a B/S architecture, the system provide the function of point cloud uploading, viewing, analysis, and danger point prediction. The research results is hoped to be applied in grid enterprise to improve the intelligent level of power grid management and maintenance.
This paper discusses the application of DIKW model in medical field, and introduces how the model transforms data into information and knowledge, and finally realizes the purpose of improving hospital performance and service quality. This paper innovatively proposes the application of TIF model in the construction of pharmaceutical platform, including information technology chain, credit chain, industrial chain and financial chain. Finally, the paper establishes the performance evaluation index system, and puts forward the conclusion and prospect. Through these methods, hospitals can better understand their operations, improve service quality and efficiency, and thus provide better medical services to patients.
In recent years, embedded platforms became attractive targets to deploy machine learning (ML) -empowered control and processing systems. However, securing a high performance executability to satisfy the hard real-time constraints of such systems on resource-limited platforms, such as FPGAs, is a challenging task. This paper introduces a methodology for deploying hardware-accelerated, adaptable convolutional neural networks (CNN) on embedded FPGA platforms. It enables automated synthesis of hardware IPs, instantiation of CNN architectures and mapping of the CNN layers processing to hardware IPs. This will result in iteration-free deployment reducing the expensive cost of HW synthesis, so that the acceleration hardware IPs are synthesized once and configured at runtime following the CNN architecture. To demonstrate the applicability and assess the performance of our deployment model, we implemented and deployed a segment-based acceleration of a image classification CNN on Xilinx ZYBO Z7 FPGA board. Among others, we have analyzed the computation performance, accuracy and trade-offs between CNN size, image segmentation size, resources utilization and scalability.
This paper studies GPU-based implementations of CRYSTALS-Dilithium (Dilithium) algorithm, which is one of four post-quantum algorithms that NIST has standardized. We focus on the scenarios of batch processing and explore low latency implementations by parallelizing the critical components of Dilithium with the consideration of overhead due to inter-thread data sharing. We also investigate the techniques of using GPU memories and warp-level instructions for data sharing in GPU-based implementations of Dilithium. All of the efforts lead to effective low latency implementations that are suited to cloud applications. Finally, we conduct evaluations on two testbeds with NVIDIA GeForce RTX 3060 and RTX A4000, respectively. The experimental results show that our low latency implementations save up to 41 percent (resp. 33 percent) latency at low task loads on the former testbed (resp. the latter testbed) when compared with the baseline implementation. We also provide engineers with a practical strategy to achieve better overall performance for applications that the number of arrived tasks is not predictable.
Job scheduling is a critical component of workload management systems that can significantly influence system performance, e.g., in HPC clusters. The scheduling objectives are often mixed, such as maximizing resource utilization and minimizing job waiting time. An increasing number of researchers are moving from heuristic-based approaches to Deep Reinforcement Learning approaches in order to optimize scheduling objectives. However, the job scheduler's state space is partially observable to a DRL-based agent because the job queue is practically unbounded. The agent's observation of the state space is constant in size since the input size of the neural networks is predefined. All existing solutions to this problem intuitively allow the agent to observe a fixed window size of jobs at the head of the job queue. In our research, we have seen that such an approach can lead to “window staleness” where the window becomes full of jobs that can not be scheduled until the cluster has completed sufficient work. In this paper, we propose a novel general technique that we call split window, which allows the agent to observe both the head and tail of the queue. With this technique, the agent can observe all arriving jobs at least once, which completely eliminates the window staleness problem. By leveraging the split window, the agent can significantly reduce the average job waiting time and average queue length, alternatively allowing the use of much smaller windows and, therefore, faster training times. We show a range of simulation results using HPC job scheduling trace data that supports the effectiveness of our technique.
This paper proposes a visualization function for developers in volunteer computing. In recent years, information systems such as e-Learning systems and groupware have been introduced in companies and educational institutions to promote DX, but the introduction and operation of these systems incur a large cost burden. Therefore, we are developing a distributed information system that can be introduced and operated at low cost by utilizing surplus computers (idle computers) in an organization. Idle computers are unstable depending on the operations of their original users and have different performances. In order to use idle computers efficiently, it is necessary to improve the performance of the system and modify it to add new functions, taking into account the differences in behavior and performance of each machine. In this paper, visualization for developers to easily check the behavior and performance of a computer in an idle state is developed, and its usefulness is evaluated through experiments using a real system.
Inverse materials design can be viewed as a reverse engineering process of material constituents from a user given set of targets characterizing material properties. Machine learning techniques could be used to map a feature space $x$ of material properties to a contextual latent space $z$ over an object space $O$ , and then reconstruct a distinct object space $O^{\prime}$ over the latent space $z$ to maximize the context $c$ . In this paper, we introduce a new machine learning tool, called MatFlow, for inverse material design using machine learning. In MatFlow, we first learn the latent space $z$ characterizing a context feature set $c$ . MatFlow then helps identify novel materials $O^{\prime}$ over the latent space $z$ with a potential to exceed the contextual threshold $\theta$ without destabilizing the latent space. We explain MatFlow features and its capabilities using an application in quantum dye material discovery. The main focus of this paper is developing a computational strategy to identify $z$ in the context of $c$ , and inform the characteristics of $z$ space values of $O^{\prime}$ most likely to meet the contextual threshold $\theta$ .
To compare the safety, effectiveness and effect of the AI early warning system and the traditional fetal monitoring system. Methods: Establish and deploy AI remote fetal monitoring system; From January 1, 2022 to December 31, 2022, 440 pregnant women in the third trimester of pregnancy admitted to the Maternal and Child Health Hospital of Haikou City and meeting the admission criteria were selected and randomly assigned to the artificial intelligence early warning remote fetal visit group 220 cases and the traditional group 220 cases. In the AI group, remote fetal monitoring system was used for examination and treatment, while in the traditional group, pregnant women went to the hospital for examination and delivery according to the usual standard procedures. The effectiveness and safety of the AI-early warning impromptu fetal heart test system were observed, and the rates of perinatal adverse outcomes (low birth weight, perinatal death, premature delivery, neonatal asphyxia, cord blood oxygen saturation and fetal distress) of pregnant women in the two groups were compared. Results: In the test of artificial intelligence early warning fetal monitoring system, the AI group detected 332 normal fetal cardiogram cases of pregnant women, 206 suspected pathological changes in 18 cases; In the traditional group, 421 cases of normal fetal cardiogram were detected, 117 cases of suspected pathological changes were detected in 16 cases. The sensitivity and specificity of normal pregnant women (true positive was normal group, false negative was suspicious + lesion) were 81.55% and 96.98% respectively. The sensitivity and specificity of pregnant women with abnormal fetal monitoring map were 100% and 82%. The low birth weight rate was 6/220 in the AI group and 13/220 in the control group, with a total value of 2.695 (p value 0. 101). Perinatal death was 0 in both groups. The rate of preterm infants in AI group was 7/220, compared with 15/220 in control group, and peason2 was 3.062,p value 0.08; Neonatal asphyxia rate was 1/220 in the AI group and 0/220 in the control group, and the exact detection rate by Fisher was p 0. 3 72. The low oxygen saturation rate of umbilical cord blood was 3/220 in the AI group and 2/220 in the control group. The p value of Fisher's accurate detection was 1.0. The fetal distress rate was 50/220 in the AI group and 76/220 in the control group, with a total of 7.518 (p value 0.006). Among the monitored perinatal adverse outcome indicators, only the fetal distress rate was significantly different between the two groups (p =0.05). Conclusions: The AI early-warning remote fetal care system is as safe and effective as the traditional fetal care system, which is helpful to break the time and space limitations of the traditional fetal care system and to sinking high-quality medical resources to the primary care. Remote fetal heart monitoring with ai warning can improve the adverse perinatal outcomes of fetal distress.
Efficient allocation of funds is crucial for enhancing the quality of postgraduate education. The DIKWP model, integrating Data, Information, Knowledge, Wisdom, and Practice, offers a comprehensive framework for decision-making in fund allocation. Through data collection, information processing, knowledge synthesis, and the application of wisdom, this model aids in making informed decisions regarding fund distribution. The study discusses the allocation of funds across key areas such as faculty development, research support, student scholarships, and infrastructure enhancement. By utilizing the DIKWP model, universities and educational institutions can optimize the allocation of funds to maximize the impact on postgraduate education quality. This research contributes to the advancement of fund allocation strategies in the context of postgraduate education, fostering a more efficient and transparent system. It offers a holistic approach to decision-making, ensuring that available resources are used effectively to support the development of academic faculty, encourage research excellence, provide financial aid to students, and improve infrastructure.
Nowadays, networks are increasingly reliant on software frameworks and virtualization. To obtain relevant pre-dictions of the behavior of their protocols, network emulation tools play a crucial role. However, as networks grow in size and complexity, the emulation task demands more physical resources such as CPU and memory. Consequently, a single physical machine is no longer sufficient to handle large-scale network emulation. Instead, distributed network emulation tools must be employed for resource-intensive network emulation tasks. In resource-intensive distributed network emulation, the physical resource allocation is NP-hard to perform appropriately. In this paper, we propose SCBG (spectral clustering based greedy node placement algorithm) as a means to enhance the bandwidth utilization between physical nodes in distributed emulation. SCBG aims to address the communication bottleneck in distributed network simulation, surpassing the algorithm proposed by Distrinet, while also improving the algorithm's execution speed. Additionally, SCBG incorporates optimization for time dilation when physical bandwidth resources are severely insufficient. This optimization leads to a reduction in the additional time required for network simulation after applying time dilation. Experimental results demonstrate that SCBG surpasses the algorithm in Distrinet across a diverse range of intricate large-scale networks.
In order to quickly and accurately synchronize the Orthogonal Frequency Division Multiplexing (OFDM)system, this paper mainly analyzes and studies the timing synchronization method based on the training sequence, and proposes a Carrier Frequency Offset (CFO) synchronization scheme using the pilot structure, and the whole scheme implements two modes: coarse estimation and fine estimation, in the coarse estimation, a wide range of CFO including Integer Carrier Frequency Offset(IFO) is estimated, in the detailed estimation, only fine CFO estimation is performed, and the relevant peaks obtained during timing synchronization are used for frequency offset estimation; Secondly, the quadratic interpolation algorithm is used as the frequency offset estimation algorithm, which is superior to the fast Fourier transform (FFT) algorithm. Theoretical analysis and simulation results show that under Gaussian channel and Rayleigh channel, the timing estimation and frequency offset estimation of the improved algorithm have lower mean squared error, and the range of integer and fractional frequency offset estimation is expanded, which reduces the computational complexity of the system, and the algorithm is better than the FFT algorithm,
This research work aims to develop an analytical approach for optimizing team formation and predicting team performance in a competitive environment based on data on the competitors' skills prior to the team formation. There are several approaches in scientific literature to optimize and predict a team's performance. However, most studies employ fine-grained skill statistics of the individual members or constraints such as teams with a set group of members. Currently, no research tackles the highly constrained domain of the FIRST Robotics Competition. This research effort aims to fill this gap by providing an analytical method for optimizing and predicting team performance in a competitive environment while allowing these constraints and only using metrics on previous team performance, not on each individual member's performance. We apply our method to the drafting process of the FIRST Robotics competition, a domain in which the skills change year-over-year, team members change throughout the season, each match only has a superficial set of statistics, and alliance formation is key to competitive success. First, we develop a method that could extrapolate individual members' performance based on overall team performance. An alliance optimization algorithm is developed to optimize team formation and a deep neural network model is trained to predict the winning team, both using highly post-processed real-world data. Our method is able to successfully extract individual members' metrics from overall team statistics, form competitive teams, and predict the winning team with 84.08% accuracy.
Loop closing is a key component in SLAM systems to reduce drift accumulations. Most SLAM systems achieve this by using only low-level geometric features of the scene, leaving the high-level features unused. This paper proposes a combinational approach of panoptic information and Scan Context++ to improve the accuracy of loop closure detection. Integrated into the SC-LeGO-LOAM algorithm, the proposed approach is able to exploit LiDAR odometry and panoptic information to perform loop closure detection as well as pose estimation and mapping. Experimental results showed that system was able to leverage panoptic information to detect loops, showing improvement in resulted maps. However, in certain environments, such as environments with reverse loops, the system suffered and resulted in slightly greater drifts.
Modern complex PC applications access the Internet and can produce unwanted network traffic. Application firewalls or personal firewalls can monitor communications on users' PCs and block such unwanted communication. Because conventional application firewalls are implemented using OS APIs, they are bypassable. This paper describes an implementation method of a non-bypassable application firewall using virtualization technologies. The proposed method runs a virtual machine (VM) for each application and monitors network traffic with a virtual switch. The controller of the virtual switch interacts with a user and allows the user to edit firewall rules through a graphical user interface (GUI). The controller translates these rules into forwarding table entries of the virtual switch on demand. This on-demand feature makes it easy to write firewall rules with domain names, which can include wildcards. This firewall does not depend on any code in VMs, and its controller is isolated by the virtual machine monitor (VMM). If the VMM and virtual switch have no vulnerability, this firewall is non-bypassable. Based on the proposed method, an application firewall has been implemented using Linux Qemu KVM as the VMM and Open vSwitch as the virtual switch. Experimental results show that the proposed method is feasible in a current powerful PC and Internet access environment.
Recommendation systems offer a solution to problems such as information overload and lack of relevant information, thereby enhancing sales and improving users satisfaction. Collaborative filtering (CF) uses the preferences of a known user group to predict the preferences of unknown users. At present, many related models have been proposed, with matrix and CP factorizations being particularly popular. But in practical recommendation applications, matrix decomposition is difficult to deal with high-dimensional data, and CP decomposition is limited by its few parameters. To optimize the efficacy of recommendations while still retaining a low level of complexity, we propose employing a tensor ring (TR) decomposition framework for CF recommendation. In this paper, TR decomposition the original tensor to obtain core tensors and a rank vector. To minimize the rating error, a loss function is constructed, and stochastic gradient descent is used to repeatedly update each parameter. In addition, to protect user sensitive information, we employ Laplace random noise to disturbe ratings. By controlling the value of the privacy budget, a balance is achieved between the preservation of data privacy and the utility of data. Extensive experiments show that our approach not only improves recommendations but also protects users privacy by using this perturbation technique.
