Pub Date : 2023-03-01DOI: 10.1109/ICTAS56421.2023.10082731
Regner Sabillon, Juan-Ramón Bermejo Higuera
This article presents the results of one empirical study that evaluated the validation of the CyberSecurity Audit Model (CSAM) for the second time in a different Canadian higher education institution. CSAM is utilized for conducting cybersecurity audits in medium or large organizations or a Nation State to evaluate and measure cybersecurity assurance, maturity, and cyber readiness. The authors review best practices and methodologies of global leaders in the cybersecurity assurance and audit arena, that puts in evidence the lack of universal guidelines to conduct extensive cybersecurity audits and the detection of existing weaknesses in general programs to deliver cybersecurity awareness training. The architecture of CSAM is described in central sections. CSAM has been tested, implemented, and validated in three research scenarios (1) a single cybersecurity domain audit (Awareness Education), (2) Cybersecurity audit of several domains (Governance and Strategy, Legal and compliance, Cyber Risks, Frameworks and Regulations, Incident Management, Cyber Insurance and Evolving Technologies) and (3) Cybersecurity audit of all model domains The study concludes by showing how the validation of the model allows to report significant information for future decision making that the target organization may correct cybersecurity weaknesses or to improve cybersecurity domains and controls.
{"title":"New Validation of a Cybersecurity Model to Audit the Cybersecurity Program in a Canadian Higher Education Institution","authors":"Regner Sabillon, Juan-Ramón Bermejo Higuera","doi":"10.1109/ICTAS56421.2023.10082731","DOIUrl":"https://doi.org/10.1109/ICTAS56421.2023.10082731","url":null,"abstract":"This article presents the results of one empirical study that evaluated the validation of the CyberSecurity Audit Model (CSAM) for the second time in a different Canadian higher education institution. CSAM is utilized for conducting cybersecurity audits in medium or large organizations or a Nation State to evaluate and measure cybersecurity assurance, maturity, and cyber readiness. The authors review best practices and methodologies of global leaders in the cybersecurity assurance and audit arena, that puts in evidence the lack of universal guidelines to conduct extensive cybersecurity audits and the detection of existing weaknesses in general programs to deliver cybersecurity awareness training. The architecture of CSAM is described in central sections. CSAM has been tested, implemented, and validated in three research scenarios (1) a single cybersecurity domain audit (Awareness Education), (2) Cybersecurity audit of several domains (Governance and Strategy, Legal and compliance, Cyber Risks, Frameworks and Regulations, Incident Management, Cyber Insurance and Evolving Technologies) and (3) Cybersecurity audit of all model domains The study concludes by showing how the validation of the model allows to report significant information for future decision making that the target organization may correct cybersecurity weaknesses or to improve cybersecurity domains and controls.","PeriodicalId":158720,"journal":{"name":"2023 Conference on Information Communications Technology and Society (ICTAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130093023","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 : 2023-03-01DOI: 10.1109/ICTAS56421.2023.10082736
Jean De La Croix Ntivuguruzwa, T. Ahmad
Technology advancements made machine learning algorithms crucial to solving complex problems. Deep learning, a machine learning paradigm to design convolutional neural networks (CNNs), achieves promising performance in detecting confidential data, known as steganalysis. However, the existing steganalysis CNNs have not achieved optimal performance detecting accuracy and network stability. In this research, we propose a new approach within CNN to improve the secret data detection accuracy by optimizing the local features in the feature extraction stage of the spatial domain images. The performance is evaluated using the Break Our Steganographic System Base (BOSSBase) dataset with two standard adaptive steganography algorithms employing low payload capacities of 0.2 and 0.4 bits per pixel. The experimental results outperform the results of the previously published works in accuracy and network stability. The detection accuracy is improved in a range between 2.1% to 3.6%.
{"title":"Toward Hidden Data Detection via Local Features Optimization in Spatial Domain Images","authors":"Jean De La Croix Ntivuguruzwa, T. Ahmad","doi":"10.1109/ICTAS56421.2023.10082736","DOIUrl":"https://doi.org/10.1109/ICTAS56421.2023.10082736","url":null,"abstract":"Technology advancements made machine learning algorithms crucial to solving complex problems. Deep learning, a machine learning paradigm to design convolutional neural networks (CNNs), achieves promising performance in detecting confidential data, known as steganalysis. However, the existing steganalysis CNNs have not achieved optimal performance detecting accuracy and network stability. In this research, we propose a new approach within CNN to improve the secret data detection accuracy by optimizing the local features in the feature extraction stage of the spatial domain images. The performance is evaluated using the Break Our Steganographic System Base (BOSSBase) dataset with two standard adaptive steganography algorithms employing low payload capacities of 0.2 and 0.4 bits per pixel. The experimental results outperform the results of the previously published works in accuracy and network stability. The detection accuracy is improved in a range between 2.1% to 3.6%.","PeriodicalId":158720,"journal":{"name":"2023 Conference on Information Communications Technology and Society (ICTAS)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122535279","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 : 2023-03-01DOI: 10.1109/ICTAS56421.2023.10082724
Shaolin Lee Govender, Seena Joseph, Alveen Singh
Potholes are an increasing and persistent challenge plaguing the timely upkeep of vital road infrastructure. Millions of money are lost each year on repairing damages and using alternate routes with longer travel times resulting from potholes. Early, accurate, and frugal means of pothole detection have a significant role in improving the quality and safety of a road transport network. In recent years machine learning has received much attention in underpinning pothole detection systems. This has resulted in a plethora of machine learning-based detection systems with little agreement on which are the best performing. This paper compares six machine learning algorithms to determine the most suitable for pothole detection when using an online dataset. Additionally, the ideal hyperparameter tuning of each machine learning algorithm is determined. The experimental results in this study demonstrate that the hyperparameter adjustment of machine learning algorithms has varying effects on pothole detection. The KNN algorithm is the best-performing machine learning algorithm with hyperparameter tuning achieving 80%, 76%, 78%, and 77% respectively for accuracy, precision, recall, and F1-Score with an average runtime of 0.11 minutes. The lowest-performing machine learning algorithm is the NB algorithm which achieved an accuracy of 73%, precision of 66%, recall of 74%, and F1-Score of 69% with an average runtime of 0.01 minutes. Overall the machine learning algorithm with hyperparameter tuning has accuracy, precision, recall, and F1-scores closely correlated as compared to machine learning algorithms without hyperparameter tuning.
{"title":"Effect of hyperparameter tuning on classical machine learning models in detecting potholes","authors":"Shaolin Lee Govender, Seena Joseph, Alveen Singh","doi":"10.1109/ICTAS56421.2023.10082724","DOIUrl":"https://doi.org/10.1109/ICTAS56421.2023.10082724","url":null,"abstract":"Potholes are an increasing and persistent challenge plaguing the timely upkeep of vital road infrastructure. Millions of money are lost each year on repairing damages and using alternate routes with longer travel times resulting from potholes. Early, accurate, and frugal means of pothole detection have a significant role in improving the quality and safety of a road transport network. In recent years machine learning has received much attention in underpinning pothole detection systems. This has resulted in a plethora of machine learning-based detection systems with little agreement on which are the best performing. This paper compares six machine learning algorithms to determine the most suitable for pothole detection when using an online dataset. Additionally, the ideal hyperparameter tuning of each machine learning algorithm is determined. The experimental results in this study demonstrate that the hyperparameter adjustment of machine learning algorithms has varying effects on pothole detection. The KNN algorithm is the best-performing machine learning algorithm with hyperparameter tuning achieving 80%, 76%, 78%, and 77% respectively for accuracy, precision, recall, and F1-Score with an average runtime of 0.11 minutes. The lowest-performing machine learning algorithm is the NB algorithm which achieved an accuracy of 73%, precision of 66%, recall of 74%, and F1-Score of 69% with an average runtime of 0.01 minutes. Overall the machine learning algorithm with hyperparameter tuning has accuracy, precision, recall, and F1-scores closely correlated as compared to machine learning algorithms without hyperparameter tuning.","PeriodicalId":158720,"journal":{"name":"2023 Conference on Information Communications Technology and Society (ICTAS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126179273","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 : 2023-03-01DOI: 10.1109/ICTAS56421.2023.10082745
S. T. Rakkesh, A. Weerasinghe, R. Ranasinghe
Metropolitan areas and traffic congestion have grown hand-in-hand with the expansion of human populations around the world. The same factors that encourage people to gather in urban areas also contributed to the intolerable levels of traffic congestion on city streets. To reduce traffic congestion and enhance localized regional traffic flows, new research initiatives should be explored which leads to successful solutions. These solutions need to be repeatedly tested, which demands for a sizable increase in support staff engagement and substantiable infrastructure amendments to evaluate novel solutions. Typically, it is not practical to conduct frequent trials on day-to-day live traffic in urban areas. Hence, simulators are essential in traffic study, aiding in the evaluation of suggested solutions. However, relying solely on simulation results of a single simulator could result in erroneous conclusions, because of the structural limitations they pose in accurately simulating every complex detail of a traffic environment. In this paper, we make use of a heterogeneous toolset that includes three dissimilar simulators that assess traffic flows in different perspectives from microscopic, mesoscopic, and macroscopic viewpoints and propose how a heterogenous toolset can be used to get more insights by using two sample study regions from Sri Lanka and India.
{"title":"Enhancing Traffic Simulations Analysis Efficacy using Multiperspective Heterogeneous Toolset","authors":"S. T. Rakkesh, A. Weerasinghe, R. Ranasinghe","doi":"10.1109/ICTAS56421.2023.10082745","DOIUrl":"https://doi.org/10.1109/ICTAS56421.2023.10082745","url":null,"abstract":"Metropolitan areas and traffic congestion have grown hand-in-hand with the expansion of human populations around the world. The same factors that encourage people to gather in urban areas also contributed to the intolerable levels of traffic congestion on city streets. To reduce traffic congestion and enhance localized regional traffic flows, new research initiatives should be explored which leads to successful solutions. These solutions need to be repeatedly tested, which demands for a sizable increase in support staff engagement and substantiable infrastructure amendments to evaluate novel solutions. Typically, it is not practical to conduct frequent trials on day-to-day live traffic in urban areas. Hence, simulators are essential in traffic study, aiding in the evaluation of suggested solutions. However, relying solely on simulation results of a single simulator could result in erroneous conclusions, because of the structural limitations they pose in accurately simulating every complex detail of a traffic environment. In this paper, we make use of a heterogeneous toolset that includes three dissimilar simulators that assess traffic flows in different perspectives from microscopic, mesoscopic, and macroscopic viewpoints and propose how a heterogenous toolset can be used to get more insights by using two sample study regions from Sri Lanka and India.","PeriodicalId":158720,"journal":{"name":"2023 Conference on Information Communications Technology and Society (ICTAS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115883579","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 : 2023-03-01DOI: 10.1109/ICTAS56421.2023.10082747
Zinhle Mthimkhulu, H. Adebanjo, Timothy T. Adeliyi
Pipe inspection, according to the literature, is not the cleanest or safest job in the world, as inspectors must perform this critical activity in hazardous and difficult situations. As time-consuming as it is, they must be inspected because they are vulnerable to problems such as cracks and corrosion, which jeopardize their integrity. They must also be inspected regularly to ensure reliable operation and the safety of workers, equipment, and the environment. Inspection is essential because it monitors and maintains the integrity of aging infrastructure while also ensuring that it operates safely and without endangering the health of plant operators. Many corporations, mostly in developing countries, continue to use traditional oil and gas industry procedures to detect and repair leaks in pipeline networks, even though such approaches are time-consuming and dangerous to humans. The goal of this research is to create a frugal inspection robot for detecting in-pipe leaks in the oil and gas industry. In addition, using the robot's acquired images, an image processing technique will be used to detect in-pipe leaks. The frugal robot will be compared to industrial in-pipe inspection robots such as Pig, wheeled, walker/legged, and wall-pressed in terms of cost, flexibility, size, stability, and vertical mobility. According to the study's findings, the frugal inspection robot can detect in-pipe leaks.
{"title":"Designing A Frugal Inspection Robot for Detecting In-Pipe Leaks in The Oil And Gas Sector","authors":"Zinhle Mthimkhulu, H. Adebanjo, Timothy T. Adeliyi","doi":"10.1109/ICTAS56421.2023.10082747","DOIUrl":"https://doi.org/10.1109/ICTAS56421.2023.10082747","url":null,"abstract":"Pipe inspection, according to the literature, is not the cleanest or safest job in the world, as inspectors must perform this critical activity in hazardous and difficult situations. As time-consuming as it is, they must be inspected because they are vulnerable to problems such as cracks and corrosion, which jeopardize their integrity. They must also be inspected regularly to ensure reliable operation and the safety of workers, equipment, and the environment. Inspection is essential because it monitors and maintains the integrity of aging infrastructure while also ensuring that it operates safely and without endangering the health of plant operators. Many corporations, mostly in developing countries, continue to use traditional oil and gas industry procedures to detect and repair leaks in pipeline networks, even though such approaches are time-consuming and dangerous to humans. The goal of this research is to create a frugal inspection robot for detecting in-pipe leaks in the oil and gas industry. In addition, using the robot's acquired images, an image processing technique will be used to detect in-pipe leaks. The frugal robot will be compared to industrial in-pipe inspection robots such as Pig, wheeled, walker/legged, and wall-pressed in terms of cost, flexibility, size, stability, and vertical mobility. According to the study's findings, the frugal inspection robot can detect in-pipe leaks.","PeriodicalId":158720,"journal":{"name":"2023 Conference on Information Communications Technology and Society (ICTAS)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132481551","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：