Xiaoyi Hu, Jin Ning, Jie Yin, Jie Yang, B. Adebisi, H. Gačanin
{"title":"Efficient Malicious Traffic Classification Methods based on Semi-supervised Learning","authors":"Xiaoyi Hu, Jin Ning, Jie Yin, Jie Yang, B. Adebisi, H. Gačanin","doi":"10.1109/DSA56465.2022.00039","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00039","url":null,"abstract":"The proliferation of mobile communication systems, arrival of high-speed broadband networks and more complex network topologies have exacerbated cyber-threats. Cyber-warfare has become an aspect of modern war-fare that can no longer be overlooked. In recent years, network intrusions launched using the Internet have seriously undermined the security systems of many nations. Classifying malicious network traffic is the first step in network intrusion detection. In this paper, we propose three models using semi-supervised learning-based malicious traffic classification (MTC) methods that effectively improve the classification of traffic using a small proportion of labeled traffic data. Employing three different deep neural networks as feature extraction networks respectively, the proposed models use transductive transfer learning and domain adaptive ideas, and ladder networks as classification layers. Experimental results are provided to validate the proposed methods.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130283790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Framework for Formal Transformation and Analysis of Smart Contract Code","authors":"Hanjie Dong, Yaqiong He, H. Tao, Q. Duan","doi":"10.1109/DSA56465.2022.00140","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00140","url":null,"abstract":"The smart contract technology has drawn extensive attention in recent years. However, attributing to the immutability of blockchain, a smart contract cannot be altered once deployed on chain. Even a simple flaw in a smart contract can cause huge economic loss. Formal method can provide a reliable guarantee for the security of smart contracts. In this paper, we present a framework for formal transformation and analysis of smart contract code, aiming to facilitate the task of analyzing security issues of smart contracts. In addition, the transformation efficiency is tested and evaluated with different scales of code, which proves the practicality and effectiveness of the transformation framework.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133906052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dual-branch Attention Detection Network for Scene Text Detection","authors":"Ronghua Jiang, Zhandong Liu, Ke Li, Lu Liang","doi":"10.1109/DSA56465.2022.00085","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00085","url":null,"abstract":"At present, the complexity of the real scene, it has brought many challenges to the scene text detection. there are many problems including the diversity of the layout shape and size of the Chinese line of the natural scene image and the arbitrariness of the direction et al. Using the existing text detector, there may still be a large number of false detections; Therefore, in order to solve the above problems, we propose a dual branch attention detection network for the text detection in natural scenes based on the idea of regional regression, which simplifies the original operation steps and only needs to deal with the data containing threshold differentiation and the non-maximum suppression analysis of predicted geometry; The algorithm proposed in this paper has reached 78.88% F-measure on icdar2015 dataset and 89.02% F-measure on icdar2013 dataset","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131742990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Chinese Psychological QA Database and its Research Problems","authors":"Youren Chen, Yang Li, Ming Wen","doi":"10.1109/DSA56465.2022.00111","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00111","url":null,"abstract":"In the past, with the development of the psychological industry in China, a large number of psychological databases have emerged. This paper surveys the psychological repositories currently available at home and abroad and researches the commonly used repositories, based on which a professional question-and-answer (Q&A) psychological repository is established and provides a researchable corpus of question and answer matching and psychological classification of research paper for suicide, depression and insomnia classification. Finally, the problems faced by machine learning when applying knowledge graphs or deep learning are discussed.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127593285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Network Intrusion Detection based on RBF Neural Networks and Fuzzy Cluster","authors":"Zhiyu Liu, Meishu Luo, Baoying Ma","doi":"10.1109/DSA56465.2022.00040","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00040","url":null,"abstract":"Network Intrusion detection is a key research topic in the field of information security. In view of the shortcomings of high data dimension and low detection accuracy for traditional detection algorithm, a detection algorithm is proposed which combined fuzzy clustering and RBF neural network. The original data set is reduced effectively by fuzzy clustering algorithm, while optimal model of RBF neural network is selected by taking of the method of cross-validation. Experiments includes the intrusion data reduction, classifier optimization, algorithm accuracy and its time consumption. The results show that the proposed algorithm in this paper can effectively reduce the original data set and its classification accuracy rate of more than 90%, since the overall algorithm performs well.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131202633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jia Tang, Lin Cui, Zhenggao Pan, Chengfang Tan, Shanshan Li, Weijie Wang
{"title":"Face Image Recognition Algorithm based on Singular Value Decomposition","authors":"Jia Tang, Lin Cui, Zhenggao Pan, Chengfang Tan, Shanshan Li, Weijie Wang","doi":"10.1109/DSA56465.2022.00098","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00098","url":null,"abstract":"In face image recognition, features play a decisive role in recognition and classification. Feature extraction can describe the image, but the extracted data may contain redundant and useless information, which affects the model generalization learning. For these problems, a face image recognition algorithm with singular value decomposition is proposed. The original data is firstly decomposed by singular value decomposition with SVD algorithm, and then the k values in the top of the singular value are selected and calculated to obtain the sample information after attribute reduction, and then the result of the reduced data is classified by the model using the extreme learning machine algorithm, and finally the type corresponding to the image can be predicted by the model, and the experimental results on the ORL face image data set also prove that algorithm has a good recognition efficiency.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"306 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133261479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluation Method of Intelligent Manufacturing Capability Maturity","authors":"Ruizhi Qiu, C. Lv, Yuxue Jin","doi":"10.1109/DSA56465.2022.00142","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00142","url":null,"abstract":"Intelligent manufacturing is a new model for the development of industrial manufacturing field. It uses the integration of technical knowledge system, manufacturing system and intelligent machine system to realize the development and progress of manufacturing industry. At present, the standardization and complexity problems of intelligent manufacturing have been gradually revealed, which need to be further deepened and solved by maturity evaluation method. In terms of research methods, intelligent manufacturing has many research models, ability evaluation system and quality control is also the focus of intelligent manufacturing research. This paper proposes a method for evaluating the maturity of intelligent manufacturing capability, which evaluates the production capacity based on the maturity level and provides guidance for the subsequent development.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124139150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dongcheng Li, W. E. Wong, Shenglong Li, Matthew Chau
{"title":"Improving Search-based Test Case Generation with Local Search using Adaptive Simulated Annealing and Dynamic Symbolic Execution","authors":"Dongcheng Li, W. E. Wong, Shenglong Li, Matthew Chau","doi":"10.1109/DSA56465.2022.00047","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00047","url":null,"abstract":"DynaMOSA is an effective search-based test case generation algorithm. However, it uses an alternating variable method for local search. This method follows a greedy strategy that considers each input variable of an optimization function independently and attempts to optimize it. Some problems with this kind of search are that it can easily become stuck in the local optimal solution and its search capability becomes inadequate in the late stage of the search. Such constraints may lead to a dramatic drop in search performance. To solve these problems, this study proposed a local search algorithm based on adaptive simulated annealing and symbolic path constraints to generate test cases with high coverage for multiple testing criteria within a limited time budget. On the one hand, the simulated annealing algorithm was selected to explore the neighborhood of candidate solutions during the search. On the other hand, various simulated annealing operators were designed for the search of each statement to enhance the applicability of the algorithm in various programs. Additionally, symbolic execution was introduced as a supplement to the simulated annealing algorithm for local search to generate test cases for inputs with complex structures. Furthermore, the proposed algorithm was implemented in EvoSuite framework. From an SF110 open-source benchmarking dataset, 49 projects or 110 classes were selected according to the complexity and number of objectives of each class under test to conduct the experiments. The proposed algorithm outperformed the original algorithm in generating high coverage test cases on most projects in terms of line, mutation, and multicriteria coverage as well as search efficiency.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114803533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xinyue Wu, Hong Zhang, Tao Shi, Congran Zhang, Liang Yan
{"title":"Intelligent Software Testing based on Visual Feedback","authors":"Xinyue Wu, Hong Zhang, Tao Shi, Congran Zhang, Liang Yan","doi":"10.1109/DSA56465.2022.00109","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00109","url":null,"abstract":"GUI testing is an important means to ensure the quality of GUI software. Traditional GUI testing methods often rely on API and have limited scope of use. The introduction of computer vision technology provides a brand-new alternative, based on the image recognition of GUI elements. It can help build visual feedback mechanism to get more information about the target system and control the testing process. In this context, this paper studies intelligent software testing based on visual feedback, designs and builds a three-layer testing framework including perception layer, driver layer, and feedback layer. The results of this project can provide technical support for intelligent GUI testing, and the clear-structured framework provides a reference for subsequent research and has certain practical value.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129498791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improvement of Path Planning Algorithm based on Small Step Artificial Potential Field Method","authors":"M. Shi, Junfeng Nie","doi":"10.1109/DSA56465.2022.00116","DOIUrl":"https://doi.org/10.1109/DSA56465.2022.00116","url":null,"abstract":"In the process of controlling the behavior of multi-agent, the cooperative control between the agent obstacle avoidance algorithm and the agent is a necessary link to realize the task of multi-agent. Based on the artificial potential field method, this paper conducts formation obstacle avoidance control for multi-agent formations, analyzes the influence of its step size on path planning, and proposes two methods to optimize the path and analyze its advantages and disadvantages. Finally, the sampling path is quality checked and re-optimized by the informed RRT* algorithm.","PeriodicalId":208148,"journal":{"name":"2022 9th International Conference on Dependable Systems and Their Applications (DSA)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129595662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}