Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558882
Yasemin Turkan, F. Tek
Neuroimaging techniques, such as Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET), help to identify Alzheimer’s disease (AD). These techniques generate large-scale, high-dimensional, multimodal neuroimaging data, which is time-consuming and difficult to interpret and classify. Therefore, interest in deep learning approaches for the classification of 3D structural MRI brain scans has grown rapidly. In this research study, we improved the 3D VGG model proposed by Korolev et al. [2]. We increased the filters in the 3D convolutional layers and then added an attention mechanism for better classification. We compared the performance of the proposed approaches for the classification of Alzheimer’s disease versus mild cognitive impairments and normal cohorts on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. We observed that both the accuracy and area under curve results improved with the proposed models. However, deep neural networks are black boxes that produce predictions that require further explanation for medical usage. We compared the 3D-data interpretation capabilities of the proposed models using four different interpretability methods: Occlusion, 3D Ultrametric Contour Map, 3D Gradient-Weighted Class Activation Mapping, and SHapley Additive exPlanations (SHAP). We observed that explanation results differed in different network models and data classes.
{"title":"Convolutional Attention Network for MRI-based Alzheimer’s Disease Classification and its Interpretability Analysis","authors":"Yasemin Turkan, F. Tek","doi":"10.1109/UBMK52708.2021.9558882","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558882","url":null,"abstract":"Neuroimaging techniques, such as Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET), help to identify Alzheimer’s disease (AD). These techniques generate large-scale, high-dimensional, multimodal neuroimaging data, which is time-consuming and difficult to interpret and classify. Therefore, interest in deep learning approaches for the classification of 3D structural MRI brain scans has grown rapidly. In this research study, we improved the 3D VGG model proposed by Korolev et al. [2]. We increased the filters in the 3D convolutional layers and then added an attention mechanism for better classification. We compared the performance of the proposed approaches for the classification of Alzheimer’s disease versus mild cognitive impairments and normal cohorts on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. We observed that both the accuracy and area under curve results improved with the proposed models. However, deep neural networks are black boxes that produce predictions that require further explanation for medical usage. We compared the 3D-data interpretation capabilities of the proposed models using four different interpretability methods: Occlusion, 3D Ultrametric Contour Map, 3D Gradient-Weighted Class Activation Mapping, and SHapley Additive exPlanations (SHAP). We observed that explanation results differed in different network models and data classes.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116078874","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 : 2021-09-15DOI: 10.1109/UBMK52708.2021.9559019
A. Mukhitova, A. Yerimbetova, Nenad Mladenović
Integration of information resources to provide users with access to miscellaneous information and the ability of information management is carried out through specialized adaptive administration and user graphic web interfaces. In this paper we study the technology of creating an adaptive graphical editor of XML records to provide access to distributed heterogeneous information resources through graphical user WEB-interfaces. The methodology for creating user interfaces suitable for the structure and functionality of information sources is also described herein. The proposed XML record editor is able to visualize the full structure of an XML document as a screen form of an HTML page. The program is a server-side WEB application that provides on-screen forms for creating and editing XML documents in accordance with the selected XSD schema.
{"title":"XML Document Transformation for Data Manipulation Operations","authors":"A. Mukhitova, A. Yerimbetova, Nenad Mladenović","doi":"10.1109/UBMK52708.2021.9559019","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9559019","url":null,"abstract":"Integration of information resources to provide users with access to miscellaneous information and the ability of information management is carried out through specialized adaptive administration and user graphic web interfaces. In this paper we study the technology of creating an adaptive graphical editor of XML records to provide access to distributed heterogeneous information resources through graphical user WEB-interfaces. The methodology for creating user interfaces suitable for the structure and functionality of information sources is also described herein. The proposed XML record editor is able to visualize the full structure of an XML document as a screen form of an HTML page. The program is a server-side WEB application that provides on-screen forms for creating and editing XML documents in accordance with the selected XSD schema.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115221802","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 : 2021-09-15DOI: 10.1109/UBMK52708.2021.9559000
Anil Özberk, I. Çiçekli
As the insulting statements increase on the online platform, these negative statements create a reaction and disturb the peace of society. Offensive language detection research has been increased in recent years. This paper explores the effects of the usage of BERT models and fine-tuning techniques on offensive language detection on Turkish tweets. We emphasize the pre-trained model importance on the performance of a downstream task and the importance of the used BERT model.
{"title":"Offensive Language Detection in Turkish Tweets with Bert Models","authors":"Anil Özberk, I. Çiçekli","doi":"10.1109/UBMK52708.2021.9559000","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9559000","url":null,"abstract":"As the insulting statements increase on the online platform, these negative statements create a reaction and disturb the peace of society. Offensive language detection research has been increased in recent years. This paper explores the effects of the usage of BERT models and fine-tuning techniques on offensive language detection on Turkish tweets. We emphasize the pre-trained model importance on the performance of a downstream task and the importance of the used BERT model.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123025590","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 : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558911
Seval Capraz, Adnan Özsoy
Starting in late 2019, a highly infectious coronavirus disease spread rapidly to all over the world and caused many deaths worldwide. This disease known as COVID-19 caused more than 180 million cases including more than 4 million deaths. Numerous false reports, misinformation, and unsolicited fears in regards to coronavirus, are being circulated regularly since the outbreak of the COVID-19. We can solve some of the problems of the pandemic with new technologies like blockchain, therefore we can control its spread until an effective and affordable vaccine is found. Blockchain can combat pandemics by enabling early detection of outbreaks, protecting user privacy, and ensuring reliable medical supply chain during the outbreak tracking. When ill people are detected, it is possible to quickly and accurately share their diagnostic information and clinical presentation with blockchain. We can also hide patients’ identity while sharing that information. Anonymization is supported in blockchain and it’s stronger than other techniques. Moreover, blockchain is transparent so that every disease event can be kept tabs on transparently. There are a lot of blockchain solutions in literature which is proposed recently to combat COVID-19-like pandemics. In this study, we aim to give the details of blockchain and why we can use it for light against pandemics and review proposed solutions. We summarized the problems of pandemic and the benefits of blockchain technology. We highlighted the defects of solutions in literature and propose alternatives.
{"title":"A Review of Blockchain Based Solutions for Fight Against Pandemics","authors":"Seval Capraz, Adnan Özsoy","doi":"10.1109/UBMK52708.2021.9558911","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558911","url":null,"abstract":"Starting in late 2019, a highly infectious coronavirus disease spread rapidly to all over the world and caused many deaths worldwide. This disease known as COVID-19 caused more than 180 million cases including more than 4 million deaths. Numerous false reports, misinformation, and unsolicited fears in regards to coronavirus, are being circulated regularly since the outbreak of the COVID-19. We can solve some of the problems of the pandemic with new technologies like blockchain, therefore we can control its spread until an effective and affordable vaccine is found. Blockchain can combat pandemics by enabling early detection of outbreaks, protecting user privacy, and ensuring reliable medical supply chain during the outbreak tracking. When ill people are detected, it is possible to quickly and accurately share their diagnostic information and clinical presentation with blockchain. We can also hide patients’ identity while sharing that information. Anonymization is supported in blockchain and it’s stronger than other techniques. Moreover, blockchain is transparent so that every disease event can be kept tabs on transparently. There are a lot of blockchain solutions in literature which is proposed recently to combat COVID-19-like pandemics. In this study, we aim to give the details of blockchain and why we can use it for light against pandemics and review proposed solutions. We summarized the problems of pandemic and the benefits of blockchain technology. We highlighted the defects of solutions in literature and propose alternatives.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124565747","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}
Huge amounts of text data are produced every day. Processing text data that accumulates and grows exponentially every day requires the use of appropriate automation tools. Text classification, a Natural Language Processing task, has the potential to provide automatic text data processing. Many new models have been proposed to achieve much better results in text classification. The transformer model has been introduced recently to provide superior performance in terms of accuracy and processing speed in deep learning. In this article, we propose an improved Transformer model for text classification. The dataset containing information about the books was collected from an online resource and used to train the models. We witnessed superior performance in our proposed Transformer model compared to previous state-of-art models such as LSTM and CNN.
{"title":"Improving Text Classification with Transformer","authors":"Gokhan Soyalp, Artun Alar, Kaan Ozkanli, Beytullah Yildiz","doi":"10.1109/UBMK52708.2021.9558906","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558906","url":null,"abstract":"Huge amounts of text data are produced every day. Processing text data that accumulates and grows exponentially every day requires the use of appropriate automation tools. Text classification, a Natural Language Processing task, has the potential to provide automatic text data processing. Many new models have been proposed to achieve much better results in text classification. The transformer model has been introduced recently to provide superior performance in terms of accuracy and processing speed in deep learning. In this article, we propose an improved Transformer model for text classification. The dataset containing information about the books was collected from an online resource and used to train the models. We witnessed superior performance in our proposed Transformer model compared to previous state-of-art models such as LSTM and CNN.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116734819","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 : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558912
Lae Lae Win, Samet Tonyali
The traditional power grid becomes ‘smart’ when it is combined with the communication and information technology. Along with smart grid, the traditional meter is replaced with smart meter. Smart meters play an important role in energy consumption reporting and, thereby, billing. Besides smart meters, the smart grid communication network is composed of heterogeneous devices that are communicating through public networks. Therefore, smart metering communications are susceptible to cyber-attacks and privacy breaches which are still under debating. This paper gives a brief overview of smart grid, smart metering, and the communication networks. Then, the privacy and security requirements of the smart grid network are derived. The various kind of cyber-attacks are discussed, after that, the different schemes and approaches that have been proposed in previous papers are reviewed. Lastly, the open issues on security and privacy of smart grid metering communications are highlighted.
{"title":"Security and Privacy Challenges, Solutions, and Open Issues in Smart Metering: A Review","authors":"Lae Lae Win, Samet Tonyali","doi":"10.1109/UBMK52708.2021.9558912","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558912","url":null,"abstract":"The traditional power grid becomes ‘smart’ when it is combined with the communication and information technology. Along with smart grid, the traditional meter is replaced with smart meter. Smart meters play an important role in energy consumption reporting and, thereby, billing. Besides smart meters, the smart grid communication network is composed of heterogeneous devices that are communicating through public networks. Therefore, smart metering communications are susceptible to cyber-attacks and privacy breaches which are still under debating. This paper gives a brief overview of smart grid, smart metering, and the communication networks. Then, the privacy and security requirements of the smart grid network are derived. The various kind of cyber-attacks are discussed, after that, the different schemes and approaches that have been proposed in previous papers are reviewed. Lastly, the open issues on security and privacy of smart grid metering communications are highlighted.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126632085","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 : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558977
Necdet Eren Erciyes, A. K. Görür
In recent years, there has been a considerable increase in textual documents online. This increase requires the creation of highly improved machine learning methods to classify text in many different domains. The effectiveness of these machine learning methods depends on the model capacity to understand the complex nature of the unstructured data and the relations of features that exist. Many different machine learning methods were proposed for a long time to solve text classification problems, such as SVM, kNN, and Rocchio classification. These shallow learning methods have achieved doubtless success in many different domains. For big and unstructured data like text, deep learning methods which can learn representations and features from the input data wtihout using any feature extraction methods have shown to be one of the major solutions. In this study, we explore the accuracy of recent recommended deep learning methods for multi-label text classification starting with simple RNN, CNN models to pretrained transformer models. We evaluated these methods’ performances by computing multi-label evaluation metrics and compared the results with the previous studies.
{"title":"Deep Learning Methods with Pre-Trained Word Embeddings and Pre-Trained Transformers for Extreme Multi-Label Text Classification","authors":"Necdet Eren Erciyes, A. K. Görür","doi":"10.1109/UBMK52708.2021.9558977","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558977","url":null,"abstract":"In recent years, there has been a considerable increase in textual documents online. This increase requires the creation of highly improved machine learning methods to classify text in many different domains. The effectiveness of these machine learning methods depends on the model capacity to understand the complex nature of the unstructured data and the relations of features that exist. Many different machine learning methods were proposed for a long time to solve text classification problems, such as SVM, kNN, and Rocchio classification. These shallow learning methods have achieved doubtless success in many different domains. For big and unstructured data like text, deep learning methods which can learn representations and features from the input data wtihout using any feature extraction methods have shown to be one of the major solutions. In this study, we explore the accuracy of recent recommended deep learning methods for multi-label text classification starting with simple RNN, CNN models to pretrained transformer models. We evaluated these methods’ performances by computing multi-label evaluation metrics and compared the results with the previous studies.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126971288","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 : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558985
Onur Ülkü, Necip Gözüaçik, Senem Tanberk, M. Aydin, A. Zaim
Software system admins depend on log data for understanding system behavior, monitoring anomalies, tracking software bugs, and malfunctioning detection. Log analysis based on machine learning techniques enables to transform of raw logs into meaningful information that helps the DevOps team and administrators to solve problems. Al ensures to group similar logs together and keeps periodic logs more organized and sorted, allowing us to get to where we need to look faster. In this paper, we present a log classification system on log data generated by VoIP (Voice over Internet Protocol) soft-switch product. In this way, we targeted to detect the problem, direct it to the relevant department, allocate resources, and solve software bugs faster and more efficiently. Machine learning algorithms such as Linear Classifiers, Support Vector Machines, Decision Tree, Random Forest, Boosting, K-Nearest Neighbors, and Multilayer Perceptron are used for log classification.
{"title":"Software Log Classification in Telecommunication Industry","authors":"Onur Ülkü, Necip Gözüaçik, Senem Tanberk, M. Aydin, A. Zaim","doi":"10.1109/UBMK52708.2021.9558985","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558985","url":null,"abstract":"Software system admins depend on log data for understanding system behavior, monitoring anomalies, tracking software bugs, and malfunctioning detection. Log analysis based on machine learning techniques enables to transform of raw logs into meaningful information that helps the DevOps team and administrators to solve problems. Al ensures to group similar logs together and keeps periodic logs more organized and sorted, allowing us to get to where we need to look faster. In this paper, we present a log classification system on log data generated by VoIP (Voice over Internet Protocol) soft-switch product. In this way, we targeted to detect the problem, direct it to the relevant department, allocate resources, and solve software bugs faster and more efficiently. Machine learning algorithms such as Linear Classifiers, Support Vector Machines, Decision Tree, Random Forest, Boosting, K-Nearest Neighbors, and Multilayer Perceptron are used for log classification.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127300689","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 : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558944
N. Ozkan, Kübra Bulut, M. Gök, G. Özer
it is common to encounter formations of IT processes that locate in and are operated by business units, outside of IT units’ control, so called shadow IT. Although it has several advantages, it also brings us a grey area that needs to be controlled properly. Otherwise, it can lead to high risks, financial and reputational losses. In this paper, we present the development of an IT governance and management system including an accompanying control approach for shadow IT in Kuveyt Turk Participation Bank based on the two main projects experienced by the bank. After defining shadow IT for the bank, we deliver the problem with a risk aspect, then, elaborate on selected control approach with its reasoning, convey establishment of related governance model and processes and finally discuss on the topic with general terms, to further give insights to organizations in the similar context. Controlling shadow IT has largely been under-emphasized so far in the literature, especially for the finance sector. Hopefully, this study sheds light on both practitioners and researchers by filling this gap, a bit.
{"title":"Controlling Shadow IT: Case Study from a Turkish Bank","authors":"N. Ozkan, Kübra Bulut, M. Gök, G. Özer","doi":"10.1109/UBMK52708.2021.9558944","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558944","url":null,"abstract":"it is common to encounter formations of IT processes that locate in and are operated by business units, outside of IT units’ control, so called shadow IT. Although it has several advantages, it also brings us a grey area that needs to be controlled properly. Otherwise, it can lead to high risks, financial and reputational losses. In this paper, we present the development of an IT governance and management system including an accompanying control approach for shadow IT in Kuveyt Turk Participation Bank based on the two main projects experienced by the bank. After defining shadow IT for the bank, we deliver the problem with a risk aspect, then, elaborate on selected control approach with its reasoning, convey establishment of related governance model and processes and finally discuss on the topic with general terms, to further give insights to organizations in the similar context. Controlling shadow IT has largely been under-emphasized so far in the literature, especially for the finance sector. Hopefully, this study sheds light on both practitioners and researchers by filling this gap, a bit.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132402695","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 : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558934
Ugur Nezir, Burak Lus, Gurhan Kucuk
Simultaneous multithreading (SMT) processors target resource under-utilization related performance problems of superscalar processors by allowing various datapath resources to be simultaneously shared among several threads with ease. This approach exploits thread-level parallelism on top of the well-studied instruction level parallelism. However, when datapath resources are shared among threads, there is always a possibility that corunning ill-intended programs may try to sniff on other programs with sensitive information like passwords or cryptocurrency information. By stress-testing and measuring many of the shared resources, this is quite achievable. These approaches are known as side-channel attacks. SMT-COP, a study published recently, is a secure architectural implementation based on resource scheduling that prevents these kind of attacks based on execution logic with a modest performance loss of nearly 10%. In this study, we aim to improve SMT-COP’s resource distribution scheme with several approaches, providing a quite close sense of security to that of SMT-COP while improving the performance by up to 8.86% on the average, over the original SMT-COP design.
{"title":"Improved Resource Scheduling for Lightweight SMT-COP","authors":"Ugur Nezir, Burak Lus, Gurhan Kucuk","doi":"10.1109/UBMK52708.2021.9558934","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558934","url":null,"abstract":"Simultaneous multithreading (SMT) processors target resource under-utilization related performance problems of superscalar processors by allowing various datapath resources to be simultaneously shared among several threads with ease. This approach exploits thread-level parallelism on top of the well-studied instruction level parallelism. However, when datapath resources are shared among threads, there is always a possibility that corunning ill-intended programs may try to sniff on other programs with sensitive information like passwords or cryptocurrency information. By stress-testing and measuring many of the shared resources, this is quite achievable. These approaches are known as side-channel attacks. SMT-COP, a study published recently, is a secure architectural implementation based on resource scheduling that prevents these kind of attacks based on execution logic with a modest performance loss of nearly 10%. In this study, we aim to improve SMT-COP’s resource distribution scheme with several approaches, providing a quite close sense of security to that of SMT-COP while improving the performance by up to 8.86% on the average, over the original SMT-COP design.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130825111","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：