Malicious domain names detection is an important technology in network security. Attackers mainly use domain generation algorithms (DGAs) to carry out malicious network attacks. Although DGA domain detection based on deep learning has good performance, recent studies have shown deep learning methods are vulnerable to adversarial examples. Therefore, we focus on the generation of DGA domain adversarial samples. In this paper, firstly we introduce the concept of geometric vectors into the adversarial samples and prove the effectiveness of the attack from the perspective of mathematical geometry. Secondly, we propose an algorithm of DGA domain adversarial sample generation based on the geometric perturbation, which uses the method of geometric vector to generate adversarial perturbation and adds it to DGA malicious domain name data to generate adversarial samples. To further verify the effectiveness of our algorithm, four DGA domain detection classifiers are used to test the generated adversarial samples, and the experimental results show that the classifiers are not able to resist the attacks of our method. Compared with other DGA domain adversarial sample generation methods, the proposed method has better performance.
{"title":"A Novel DGA Domain Adversarial Sample Generation Method By Geometric Perturbation","authors":"Qihe Liu, Gao Yu, Yuanyuan Wang, Zeng Yi","doi":"10.1145/3503047.3503080","DOIUrl":"https://doi.org/10.1145/3503047.3503080","url":null,"abstract":"Malicious domain names detection is an important technology in network security. Attackers mainly use domain generation algorithms (DGAs) to carry out malicious network attacks. Although DGA domain detection based on deep learning has good performance, recent studies have shown deep learning methods are vulnerable to adversarial examples. Therefore, we focus on the generation of DGA domain adversarial samples. In this paper, firstly we introduce the concept of geometric vectors into the adversarial samples and prove the effectiveness of the attack from the perspective of mathematical geometry. Secondly, we propose an algorithm of DGA domain adversarial sample generation based on the geometric perturbation, which uses the method of geometric vector to generate adversarial perturbation and adds it to DGA malicious domain name data to generate adversarial samples. To further verify the effectiveness of our algorithm, four DGA domain detection classifiers are used to test the generated adversarial samples, and the experimental results show that the classifiers are not able to resist the attacks of our method. Compared with other DGA domain adversarial sample generation methods, the proposed method has better performance.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131868564","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}
∗With the increasingly complex naval battlefields and the rapid development of artificial intelligence in the future, it has become an inevitable trend for the naval battlefield combat aid decision-making to develop toward intelligence. The purpose of the research is to embed the simulation test environment based on deep reinforcement learning technology into the combat auxiliary decision-making system, use simulation to support ongoing military decision-making operations, and provide an auxiliary decision-making reference for the commander’s multi-branch plan real-time decision-making in the emergency combat environment. Combining deep reinforcement learning and Monte Carlo tree search, the strategy network selects decision branches to reduce the search width, and the value network evaluates the naval battlefield situation to reduce the search depth. Meanwile, the self-game of reinforcement learning is used to adjust the strategy network, improve the performance of the strategy network, and use adversarial deduction to further train the value network. Finally, when the next branch decision is made, the intelligent simulation engine is used to determine the optimal branch decision under the current situation by combining the Monte Carlo tree search algorithm of the strategy network and the value network. The complexity of the information-based naval battlefield determines the importance of improving the ability to assist in combat decision-making. Research and explore the use of artificial intelligence as a commander’s assistant for real-time combat assistance decision-making, and make a way to solve the difficulties and challenges of intelligent decision-making in naval battlefields.
{"title":"Research on Intelligent Operational Assisted Decision-making of Naval Battlefield Based on Deep Reinforcement Learning","authors":"X. Zhao, Mei Yang, Cui Peng, Chaonan Wang","doi":"10.1145/3503047.3503057","DOIUrl":"https://doi.org/10.1145/3503047.3503057","url":null,"abstract":"∗With the increasingly complex naval battlefields and the rapid development of artificial intelligence in the future, it has become an inevitable trend for the naval battlefield combat aid decision-making to develop toward intelligence. The purpose of the research is to embed the simulation test environment based on deep reinforcement learning technology into the combat auxiliary decision-making system, use simulation to support ongoing military decision-making operations, and provide an auxiliary decision-making reference for the commander’s multi-branch plan real-time decision-making in the emergency combat environment. Combining deep reinforcement learning and Monte Carlo tree search, the strategy network selects decision branches to reduce the search width, and the value network evaluates the naval battlefield situation to reduce the search depth. Meanwile, the self-game of reinforcement learning is used to adjust the strategy network, improve the performance of the strategy network, and use adversarial deduction to further train the value network. Finally, when the next branch decision is made, the intelligent simulation engine is used to determine the optimal branch decision under the current situation by combining the Monte Carlo tree search algorithm of the strategy network and the value network. The complexity of the information-based naval battlefield determines the importance of improving the ability to assist in combat decision-making. Research and explore the use of artificial intelligence as a commander’s assistant for real-time combat assistance decision-making, and make a way to solve the difficulties and challenges of intelligent decision-making in naval battlefields.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129031848","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}
M. Ogbuachi, Itilekha Podder, Udo Bub, Murad Huseynli
In the field of Business Process Management (BPM), planning and executing precise process tailoring and optimization can be done through different design strategies. Even though Situational Method Engineering (SME) can provide an additional layer of constitutional knowledge, it hasn’t been explored as deeply as other traditional methods. Strategies that rely on a so-called “situational context” make use of the atomic conceptual entities known as method chunks and/or fragments from the field of Situational Method Engineering (SME). BPM, on the other hand, describes processes through representational tools that have been thoroughly used in industry and established as reliable. All of these designs have advantages and disadvantages. We analyzed several designs and proposed a synthesized framework (metamodel) that combines their strong points, while also providing a way to objectively quantify and restructure the performance of a pre-existing process/product (or optimize the creation of an entirely new one). We provide an analysis with a manufacturing organization using BPM concepts for process management/improvement and our proposed method framework, which incorporates Situational Method Engineering metamodelling and the Critical Path Method as a base for process improvement. We show here how using our proposed framework brings a flexible approach to a structured process management, helping enterprises to define, apply, store and retrieve their processes through methods/fragments, while also providing a guideline for systematic tailoring.
{"title":"A Framework for Quantifiable Process Improvement through Method Fragments in Situational Method Engineering","authors":"M. Ogbuachi, Itilekha Podder, Udo Bub, Murad Huseynli","doi":"10.1145/3503047.3503535","DOIUrl":"https://doi.org/10.1145/3503047.3503535","url":null,"abstract":"In the field of Business Process Management (BPM), planning and executing precise process tailoring and optimization can be done through different design strategies. Even though Situational Method Engineering (SME) can provide an additional layer of constitutional knowledge, it hasn’t been explored as deeply as other traditional methods. Strategies that rely on a so-called “situational context” make use of the atomic conceptual entities known as method chunks and/or fragments from the field of Situational Method Engineering (SME). BPM, on the other hand, describes processes through representational tools that have been thoroughly used in industry and established as reliable. All of these designs have advantages and disadvantages. We analyzed several designs and proposed a synthesized framework (metamodel) that combines their strong points, while also providing a way to objectively quantify and restructure the performance of a pre-existing process/product (or optimize the creation of an entirely new one). We provide an analysis with a manufacturing organization using BPM concepts for process management/improvement and our proposed method framework, which incorporates Situational Method Engineering metamodelling and the Critical Path Method as a base for process improvement. We show here how using our proposed framework brings a flexible approach to a structured process management, helping enterprises to define, apply, store and retrieve their processes through methods/fragments, while also providing a guideline for systematic tailoring.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127504328","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}
This article proposes the MASSCAH method realization for Apache Spark clustering algorithms selection and configuration. Optimization of one of the clustering quality measures is used to configure the algorithm. In the course of this study, additional clustering quality measures were implemented that are not included in the Apache Spark framework, since at the moment only the silhouette criterion is available in the framework.
{"title":"Application of the automatic selection and configuration of clustering algorithms method for the Apache Spark framework","authors":"V. Kazakovtsev, Sergey Muravyov","doi":"10.1145/3503047.3503104","DOIUrl":"https://doi.org/10.1145/3503047.3503104","url":null,"abstract":"This article proposes the MASSCAH method realization for Apache Spark clustering algorithms selection and configuration. Optimization of one of the clustering quality measures is used to configure the algorithm. In the course of this study, additional clustering quality measures were implemented that are not included in the Apache Spark framework, since at the moment only the silhouette criterion is available in the framework.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128662078","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}
Facial expression recognition has always been a challenging task. With the development of deep learning theory, facial expression recognition has brought new breakthroughs and development trends. This paper proposes a network based on attention mechanism. A mask block is designed to extract facial expression feature information, the improved residual network is used to obtain multi-scale feature information, and the convolutional block attention module (CBAM) is added to the network to pay attention to image detail features. The experimental results show that the recognition rate of the proposed network reaches 72.84% and 85.43% of the public data sets of FER2013 and RAF-DB, which effectively improves the accuracy of expression recognition.
{"title":"Facial Expression Recognition Based on Deep Learning and Attention Mechanism","authors":"Y. Ma, Chaobing Huang","doi":"10.1145/3503047.3503052","DOIUrl":"https://doi.org/10.1145/3503047.3503052","url":null,"abstract":"Facial expression recognition has always been a challenging task. With the development of deep learning theory, facial expression recognition has brought new breakthroughs and development trends. This paper proposes a network based on attention mechanism. A mask block is designed to extract facial expression feature information, the improved residual network is used to obtain multi-scale feature information, and the convolutional block attention module (CBAM) is added to the network to pay attention to image detail features. The experimental results show that the recognition rate of the proposed network reaches 72.84% and 85.43% of the public data sets of FER2013 and RAF-DB, which effectively improves the accuracy of expression recognition.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121364767","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}
As part of e-government efforts investing in public service, e-justice plays an important role in creating a fair, transparent, and efficient social environment. However, few publications have explored the factors influencing e-justice adoption. This paper develops a research model considering perceived ease of use, perceived usefulness, trust, compatibility, relative advantage and attitude as the main constructs. The proposed model is validated by using survey data gathered from 394 respondents in China. The results indicate that attitude, compatibility, relative advantage and perceived usefulness are determinants of citizen intention to adopt e-justice services. These findings are important for decision-makers from the judicial system in the formulation of e-justice adoption strategies as well as for IT developers in the implementation of e-justice projects.
{"title":"Citizen adoption of e-justice services: An empirical research in China","authors":"Jia Yu","doi":"10.1145/3503047.3503061","DOIUrl":"https://doi.org/10.1145/3503047.3503061","url":null,"abstract":"As part of e-government efforts investing in public service, e-justice plays an important role in creating a fair, transparent, and efficient social environment. However, few publications have explored the factors influencing e-justice adoption. This paper develops a research model considering perceived ease of use, perceived usefulness, trust, compatibility, relative advantage and attitude as the main constructs. The proposed model is validated by using survey data gathered from 394 respondents in China. The results indicate that attitude, compatibility, relative advantage and perceived usefulness are determinants of citizen intention to adopt e-justice services. These findings are important for decision-makers from the judicial system in the formulation of e-justice adoption strategies as well as for IT developers in the implementation of e-justice projects.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128179330","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}
Although lots of progress were made in Text Recognition /OCR in recent years, the task of font recognition is remaining challenging. The main challenge lies in the subtle difference between these similar fonts, which is hard to distinguish. This paper proposes a novel font recognizer with a pluggable module solving the font recognition task. The pluggable module hides the most discriminative accessible features and forces the network to consider other complicated features to solve the hard examples of similar fonts, called HE Block. Compared with the available public font recognition systems, our proposed method does not require any interactions at the inference stage. Extensive experiments demonstrate that HENet achieves encouraging performance, including on character-level dataset Explor all and word-level dataset AdobeVFR.
{"title":"HENet: Forcing a Network to Think More for Font Recognition","authors":"Jingchao Chen, Shiyi Mu, Shugong Xu, Youdong Ding","doi":"10.1145/3503047.3503055","DOIUrl":"https://doi.org/10.1145/3503047.3503055","url":null,"abstract":"Although lots of progress were made in Text Recognition /OCR in recent years, the task of font recognition is remaining challenging. The main challenge lies in the subtle difference between these similar fonts, which is hard to distinguish. This paper proposes a novel font recognizer with a pluggable module solving the font recognition task. The pluggable module hides the most discriminative accessible features and forces the network to consider other complicated features to solve the hard examples of similar fonts, called HE Block. Compared with the available public font recognition systems, our proposed method does not require any interactions at the inference stage. Extensive experiments demonstrate that HENet achieves encouraging performance, including on character-level dataset Explor all and word-level dataset AdobeVFR.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131630019","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：