Pub Date : 2020-12-08DOI: 10.23919/ICITST51030.2020.9351315
S. Kim
Bigdata is a dataset of which size is beyond the ability of handling a valuable raw material that can be refined and distilled into valuable specific insights. Compact data is a method that optimizes the big dataset that gives best assets without handling complex bigdata. The compact dataset contains the maximum knowledge patterns at fine grained level for effective and personalized utilization of bigdata systems without big data. The compact data method is a tailor-made design which depends on problem situations. Various compact data techniques have been demonstrated into various data-driven research area in the paper.
{"title":"Toward Compact Data from Big Data","authors":"S. Kim","doi":"10.23919/ICITST51030.2020.9351315","DOIUrl":"https://doi.org/10.23919/ICITST51030.2020.9351315","url":null,"abstract":"Bigdata is a dataset of which size is beyond the ability of handling a valuable raw material that can be refined and distilled into valuable specific insights. Compact data is a method that optimizes the big dataset that gives best assets without handling complex bigdata. The compact dataset contains the maximum knowledge patterns at fine grained level for effective and personalized utilization of bigdata systems without big data. The compact data method is a tailor-made design which depends on problem situations. Various compact data techniques have been demonstrated into various data-driven research area in the paper.","PeriodicalId":346678,"journal":{"name":"2020 15th International Conference for Internet Technology and Secured Transactions (ICITST)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122170164","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}
Pub Date : 2020-12-08DOI: 10.23919/icitst51030.2020.9351323
{"title":"Session 4: Internet Application and Technology","authors":"","doi":"10.23919/icitst51030.2020.9351323","DOIUrl":"https://doi.org/10.23919/icitst51030.2020.9351323","url":null,"abstract":"","PeriodicalId":346678,"journal":{"name":"2020 15th International Conference for Internet Technology and Secured Transactions (ICITST)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121809512","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}
Pub Date : 2020-12-08DOI: 10.23919/icitst51030.2020.9351344
{"title":"Session 8: Digital Forensics and Cyber Security","authors":"","doi":"10.23919/icitst51030.2020.9351344","DOIUrl":"https://doi.org/10.23919/icitst51030.2020.9351344","url":null,"abstract":"","PeriodicalId":346678,"journal":{"name":"2020 15th International Conference for Internet Technology and Secured Transactions (ICITST)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117147837","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}
Pub Date : 2020-12-08DOI: 10.23919/ICITST51030.2020.9351309
Huangxiaolie Liu, Dong Zhang, Hui-Bing Chen
In the field of computer vision, machine learning (ML) models have been widely used in various tasks to achieve better performance. ML models, however, do a poor job of identifying malicious inputs such as adversarial examples. Abuse adversarial examples can cause security threats in ML-based products or applications. According to the definition of adversarial examples, the feature distribution of adversarial examples and normal examples are different. Besides, classification results of adversarial examples are sensitive to additive perturbance while normal examples are robust. This provides a theoretical basis for detecting adversarial examples from its own distribution. In this paper, we summarized some adversarial attack methods and defense methods, and a detection method based on the robustness of the classification result is proposed. This detection method has relatively good performance on gradient-based adversarial attack methods and does not rely on the structure or other information of ML model, so the structure of ML models need not be modified, which has a certain significance in practical engineering.
{"title":"Towards robust classification detection for adversarial examples","authors":"Huangxiaolie Liu, Dong Zhang, Hui-Bing Chen","doi":"10.23919/ICITST51030.2020.9351309","DOIUrl":"https://doi.org/10.23919/ICITST51030.2020.9351309","url":null,"abstract":"In the field of computer vision, machine learning (ML) models have been widely used in various tasks to achieve better performance. ML models, however, do a poor job of identifying malicious inputs such as adversarial examples. Abuse adversarial examples can cause security threats in ML-based products or applications. According to the definition of adversarial examples, the feature distribution of adversarial examples and normal examples are different. Besides, classification results of adversarial examples are sensitive to additive perturbance while normal examples are robust. This provides a theoretical basis for detecting adversarial examples from its own distribution. In this paper, we summarized some adversarial attack methods and defense methods, and a detection method based on the robustness of the classification result is proposed. This detection method has relatively good performance on gradient-based adversarial attack methods and does not rely on the structure or other information of ML model, so the structure of ML models need not be modified, which has a certain significance in practical engineering.","PeriodicalId":346678,"journal":{"name":"2020 15th International Conference for Internet Technology and Secured Transactions (ICITST)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123956461","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}
Pub Date : 2020-12-08DOI: 10.23919/ICITST51030.2020.9351326
Loreen Mahmoud, R. Praveen
One of the most significant systems in computer network security assurance is the assessment of computer network security. With the goal of finding an effective method for performing the process of security evaluation in a computer network, this paper uses a deep neural network to be responsible for the task of security evaluating. The DNN will be built with python on Spyder IDE, it will be trained and tested by 17 network security indicators then the output that we get represents one of the security levels that have been already defined. The maj or purpose is to enhance the ability to determine the security level of a computer network accurately based on its selected security indicators. The method that we intend to use in this paper in order to evaluate network security is simple, reduces the human factors interferences, and can obtain the correct results of the evaluation rapidly. We will analyze the results to decide if this method will enhance the process of evaluating the security of the network in terms of accuracy.
{"title":"Network Security Evaluation Using Deep Neural Network","authors":"Loreen Mahmoud, R. Praveen","doi":"10.23919/ICITST51030.2020.9351326","DOIUrl":"https://doi.org/10.23919/ICITST51030.2020.9351326","url":null,"abstract":"One of the most significant systems in computer network security assurance is the assessment of computer network security. With the goal of finding an effective method for performing the process of security evaluation in a computer network, this paper uses a deep neural network to be responsible for the task of security evaluating. The DNN will be built with python on Spyder IDE, it will be trained and tested by 17 network security indicators then the output that we get represents one of the security levels that have been already defined. The maj or purpose is to enhance the ability to determine the security level of a computer network accurately based on its selected security indicators. The method that we intend to use in this paper in order to evaluate network security is simple, reduces the human factors interferences, and can obtain the correct results of the evaluation rapidly. We will analyze the results to decide if this method will enhance the process of evaluating the security of the network in terms of accuracy.","PeriodicalId":346678,"journal":{"name":"2020 15th International Conference for Internet Technology and Secured Transactions (ICITST)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124592489","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}
Pub Date : 2020-10-08DOI: 10.23919/ICITST51030.2020.9351335
Fabian Schillinger, C. Schindelhauer
In secure Online Social Networks (OSN), often end-to-end encryption is used to ensure the privacy of the communication. To manage, store, or transfer cryptographic keys from one device to another, encrypted private storages can be used. To gain access to such storages, login credentials, only known to the user, are needed. Losing these credentials results in a permanent loss of cryptographic keys and messages because the storage is encrypted. We present a scheme to split encrypted user storages into multiple storages. Each one can be reconstructed with the help of other participants of the OSN. The more of the storages can be reconstructed, the higher the chance of successfully reconstructing the complete private storage is. Therefore, regaining possession of the cryptographic keys used for communication is increased. We achieve high rates of successful reconstructions, even if a large fraction of the distributed shares is not accessible anymore because the shareholders are inactive or malicious.
在安全的在线社交网络(Online Social Networks, OSN)中，通常使用端到端加密来确保通信的私密性。要管理、存储或将加密密钥从一个设备传输到另一个设备，可以使用加密的私有存储。要访问这些存储，需要只有用户知道的登录凭据。丢失这些凭证将导致加密密钥和消息的永久丢失，因为存储是加密的。提出了一种将加密用户存储拆分为多个存储的方案。每个节点都可以在OSN的其他参与者的帮助下进行重构。可以重构的存储越多，成功重构完整私有存储的机会就越高。因此，重新获得用于通信的加密密钥的所有权增加了。我们实现了很高的成功重建率，即使由于股东不活跃或恶意，很大一部分分布的股票不再可访问。
{"title":"Partitioned Private User Storages in End-to-End Encrypted Online Social Networks","authors":"Fabian Schillinger, C. Schindelhauer","doi":"10.23919/ICITST51030.2020.9351335","DOIUrl":"https://doi.org/10.23919/ICITST51030.2020.9351335","url":null,"abstract":"In secure Online Social Networks (OSN), often end-to-end encryption is used to ensure the privacy of the communication. To manage, store, or transfer cryptographic keys from one device to another, encrypted private storages can be used. To gain access to such storages, login credentials, only known to the user, are needed. Losing these credentials results in a permanent loss of cryptographic keys and messages because the storage is encrypted. We present a scheme to split encrypted user storages into multiple storages. Each one can be reconstructed with the help of other participants of the OSN. The more of the storages can be reconstructed, the higher the chance of successfully reconstructing the complete private storage is. Therefore, regaining possession of the cryptographic keys used for communication is increased. We achieve high rates of successful reconstructions, even if a large fraction of the distributed shares is not accessible anymore because the shareholders are inactive or malicious.","PeriodicalId":346678,"journal":{"name":"2020 15th International Conference for Internet Technology and Secured Transactions (ICITST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129710383","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：