Log anomaly detection based on deep learning is one of the research hotspots in the field of computer security. It is foreseeable that the mimicry theory proposed by Academician Wu Jiangxing will further improve the detection capabilities of deep learning models, but will also bring high resource consumption and difficulty in application. Therefore, this paper proposes a mimic model construction method that uses the output of complex models as prior knowledge to train lightweight heterogeneous execution bodies and then integrates them. Finally, it is based on DPCNN and TextCNN as complex models and lightweight executions respectively. The experiment of the body structure mimic model proves that while reducing the number of parameters from millions to thousands, its detection accuracy and F1 value are only about 2% and 4% lower than the original model, which greatly retains the original model. The detection capability.
Distributed sensing and actuation systems research has drawn a great attention in recent years from various research communities. These systems are usually deployed in wild fields using a wireless network for the communication. Due to the shortage of power supply and bandwidth, the less communication between system components is desired since it consumes much more power comparing with local computation and uses network bandwidth. In addition, the dynamics of the deployed environments requires distributed sensing and actuation systems being self-organized, scalable, and adaptable. To achieve these desirable characteristics, this paper proposes a mobile agent approach to reduce raw data transmission over a network and increase the flexibility of a distributed sensing and actuation system. The basic ideas of the proposed mobile agent method and the framework based on a mobile agent system called Mobile-C are introduced. Mobile-C is embedded into sensor nodes consisting of an embedded computer and several expansion boards for analog/digital signal input/output and wireless communication. The advantages of using mobile agent based wireless sensor networks for intelligent structure health monitoring are discussed, and a data analysis mobile agent example is given to demonstrate the capability of such a network to dynamically deploy data analysis algorithms and reduce raw data transmission.
Amyotrophic lateral sclerosis (ALS) patients will gradually lost their motion abilities and have huge inconvenience in their daily life. In this article, an artificial throat and eye tracking based smart assistive system is presented. Through detecting eye motions and throat vibrations, the established neural network can interpret the patient's intention, and perform simple operations by a robotic arm (e.g. grasp an object). The experimental results demonstrate that the developed system can help patients obtain basic self-care ability.
The development of complex software systems has been qualitatively affected by the need to accommodate an increasing degree of flexibility, adaptability, collaboration, and autonomy. Agent technology is emerging as an alternate in building a new generation of highly distributed, open, and dynamic software systems. This research studies different aspects of agent technology. The concept, major characteristics, and application areas of agents are presented. In particular, the distinct features of mobile agents and their potential application areas are discussed. The key technical aspects of mobile agent systems are addressed, and two major mobile agent standards are described. Several notable mobile agent systems are also examined.
A mobile agent platform, Mobile-C, has been developed in the course of this research. Mobile-C is a FIPA (the Foundation for Intelligent Physical Agents) compliant mobile agent platform supporting mobile C/C++ agents. Compliance with FIPA standards ensures the interoperability of Mobile-C in a heterogeneous network. Choosing scriptable C/C++ as mobile agent language expands the potential application areas of Mobile-C, including electro-mechanical systems with interfaces to low-level hardware. Mobile-C extends FIPA specifications to support mobile agents. An embeddable C/C++ interpreter—Ch has been integrated into the system as a mobile agent execution engine. Each mobile agent runs in a separate thread through embedded Ch. The multi-thread approach significantly increases the efficiency of the system because it avoids expensive inter-process communication in the multi-process approach. Mobile-C provides communication services to support agent communication and migration through message passing. A mobile agent mobility protocol has been developed to regulate the agent migration. The system validation results have demonstrated the feasibility and applicability of the system.
Mobile-C has potential to be used to support code mobility in a wide range of applications, such as agile manufacturing systems, real-time mechatronic systems, and intelligent transportation systems. Mobile-C has been used to simulate highway traffic detection and management. The application of agent technology will significantly enhance the distributed computing and cooperation capabilities of intelligent transportation systems. The mobile agents in the system demonstrate the effectiveness of mobile agents for dynamic code deployment and remote data processing.
Abstract The rapid development of the Internet has also brought opportunities for some illegal elements. Network attackers steal sensitive information from victims through phishing webpages to obtain economic benefits. Currently, the commonly used detection methods for phishing webpages, based on blacklist detection and webpage content feature detection, have the problems of being unable to detect newly emerging phishing webpages or requiring manual extraction of webpage features. Therefore, researchers have used Convolution Neural Network (CNN) to detect phishing webpages by automatically extracting URL features. However, its method has some limitations: (1) The memory is limited when the URL is transformed into the feature matrix, and the embedding vector of new words cannot be obtained or the effective information of sensitive words is lost; (2) the long-distance dependent feature of the URL cannot be obtained. In response to the above challenges, we proposes a phishing detection method based on CNN and Bi-directional Long Short-Term Memory (Bi-LSTM) based on existing work: based on sensitive word segmentation-- comprehensively using two existing URL segmentation methods before converting URL into eigenvector matrix; adding Bi-LSTM on the basis of convolutional neural network to obtain URL long-distance dependent features. Experimental results show that this method can achieve high accuracy, recall rate and F1 value.
The development of mobile computing and the Internet of Things (IoT) has led to a surge in traffic volume, which creates a heavy burden for efficient network management. The network management requires high computational overheads to make traffic classification, which is even worse when in edge networks; existing approaches sacrifice the efficiency to obtain high-precision classification results, which are no longer suitable for limited resources edge network scenario. Given the problem, existing traffic classification generally has huge parameters and especially computational complexity. We propose a lightweight traffic classification model based on the Mobilenetv3 and improve it for an ingenious balance between performance and lightweight. Firstly, we adjust the model scale, width, and resolution to substantially reduce the number of model parameters and computations. Secondly, we embed precise spatial information on the attention mechanism to enhance the traffic flow-level feature extraction capability. Thirdly, we use the lightweight multiscale feature fusion to obtain the multiscale flow-level features of traffic. Experiments show that our model has excellent classification accuracy and operational efficiency. The accuracy of the traffic classification model designed in our work has reached more than 99.82%, and the parameter and computation amount are significantly reduced to 0.26 M and 5.26 M. In addition, the simulation experiments on Raspberry Pi prove the proposed model can realize real-time classification capability in the edge network.
With the development of modern browsing, the convenience brought by rich browser features has also produced a large number of features, which are called browser fingerprints. This article surveys the latest research results on browser fingerprinting, hoping to provide a convenient navigation for newcomers to research or apply this technology in the future. This paper first briefly introduces the browser fingerprinting technology itself, then classifies the related research on browsers, and analyzes the development of different research directions of browser fingerprinting in detail. And through the analysis of the existing results, the problems faced by different research directions are pointed out. After that, this paper introduces the application of browser fingerprint technology in detail and discusses the application achievements and technical challenges of this technology. Next, this paper introduces the theoretical tools related to the research of browser fingerprinting technology and introduces the application of different theoretical tools and practical significance. Finally, the research achievements of browser fingerprint recognition are summarized, and the future development trend is pointed out.
This paper presents the hardware and software design of a wireless sensor node for structural health monitoring. The unique features of the presented sensor node are its high computational capability, multi-modal sensing, and the combined ability for both active sensing and passive sensing. The open software architecture design approach for the upper layer application software promotes software reuse and speeds up the development cycle by employing available numerical algorithms in open software packages such as CLAPACK and numerical recipes in C. The multi-modal sensing capability allows the sensor node having a broader view of the monitoring structure with integrated information from different types of sensors.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
