Pub Date : 2024-07-26DOI: 10.3389/fcomp.2024.1434436
Ravdeep Kour, Ramin Karim, Pierre Dersin, Naveen Venkatesh
Industry 5.0 promises to revolutionize the industry by focusing on human-centric, sustainability, and resilience empowered by emerging technologies such as Artificial Intelligence (AI) and digitalization. This paradigm shift is expected to bring significant advancements in sustainability, resilience, productivity, effectiveness, efficiency, customization, reliability, safety, security, maintainability etc. However, this shift of the industrial paradigm introduces substantial cybersecurity challenges due to the increased attack surface and data sensitivity. Therefore, the objective of this paper is to conduct a thorough literature review of the recent research on cybersecurity in Industry 5.0, highlighting emerging trends, gaps, and potential solutions. To conduct this research, the authors have applied the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to investigate cybersecurity solutions in Industry 5.0. The findings reveal that conceptual research dominates, with AI, Blockchain, and Internet of Things (IoT) most prevalent but highlights a gap in linking cybersecurity to resilience and sustainability. Furthermore, the paper aims to present trends in cybersecurity research with more relevant results from 2022 to 2024. It conducts a thorough review of the literature, highlighting the evolving landscape of cybersecurity applications in Industry 5.0.
{"title":"Cybersecurity for Industry 5.0: trends and gaps","authors":"Ravdeep Kour, Ramin Karim, Pierre Dersin, Naveen Venkatesh","doi":"10.3389/fcomp.2024.1434436","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1434436","url":null,"abstract":"Industry 5.0 promises to revolutionize the industry by focusing on human-centric, sustainability, and resilience empowered by emerging technologies such as Artificial Intelligence (AI) and digitalization. This paradigm shift is expected to bring significant advancements in sustainability, resilience, productivity, effectiveness, efficiency, customization, reliability, safety, security, maintainability etc. However, this shift of the industrial paradigm introduces substantial cybersecurity challenges due to the increased attack surface and data sensitivity. Therefore, the objective of this paper is to conduct a thorough literature review of the recent research on cybersecurity in Industry 5.0, highlighting emerging trends, gaps, and potential solutions. To conduct this research, the authors have applied the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to investigate cybersecurity solutions in Industry 5.0. The findings reveal that conceptual research dominates, with AI, Blockchain, and Internet of Things (IoT) most prevalent but highlights a gap in linking cybersecurity to resilience and sustainability. Furthermore, the paper aims to present trends in cybersecurity research with more relevant results from 2022 to 2024. It conducts a thorough review of the literature, highlighting the evolving landscape of cybersecurity applications in Industry 5.0.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":"5 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141799417","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 : 2024-07-26DOI: 10.3389/fcomp.2024.1343778
Rahim Khan, Mushtaq Khan, Nadir Shah, Amal Al-Rasheed, Aftab Ahmad Khan
Internet of Things (IoT) has become an interesting research domain as numerous devices, preferably equipped with sensors, communication, and actuator modules, are deployed to capture real-time data in the different application areas, such as smart healthcare and industries. These devices have the built-in capacity to directly interact with the physical phenomenon and report any unusual situation within their respective coverage areas, i.e., monitoring a critical patient in the smart hospital but direct communication with a common destination module is not guaranteed and could possibly be very challenging if two or more devices, preferably those in closed proximity, are interested to transmit simultaneously. Therefore, in this manuscript, we are going to present a hybrid slot allocation approach, which is specifically designed for those devices resided in neighborhood and are eager to communication concurrently with a common destination device, i.e., server. In the beginning, the k-mean clustering algorithm is used to group these devices into clusters where server is forced to collect data from devices deployed in the respective coverage areas. Thus, every server generates dedicated slots for active devices and an additional slot for server(s). Similarly, the proposed neighborhood-enabled time division multiple access (TDMA) has the flexibility of assigning multiple slots to a requesting device if available, which is needed in scenarios, such as detection of pest in the field. Additionally, a member device is allowed to migrate (if needed and possible) from one server's coverage region to another. Simulation results confirmed that the proposed approach is better than the existing algorithms (opportunistic TDMA, hybrid TDMA, and non-orthogonal multiple access), particularly in terms of bandwidth, end-to-end delay, and empty slot utilization. The proposed scheme has improved bandwidth and empty slot utilization, which are approximately 15% and 12%, respectively, whereas it has achieved approximately 94.89% utilization of the available slots which was previously 93.4%.
{"title":"Device-enabled neighborhood-slot allocation for the edge-oriented Internet of Things","authors":"Rahim Khan, Mushtaq Khan, Nadir Shah, Amal Al-Rasheed, Aftab Ahmad Khan","doi":"10.3389/fcomp.2024.1343778","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1343778","url":null,"abstract":"Internet of Things (IoT) has become an interesting research domain as numerous devices, preferably equipped with sensors, communication, and actuator modules, are deployed to capture real-time data in the different application areas, such as smart healthcare and industries. These devices have the built-in capacity to directly interact with the physical phenomenon and report any unusual situation within their respective coverage areas, i.e., monitoring a critical patient in the smart hospital but direct communication with a common destination module is not guaranteed and could possibly be very challenging if two or more devices, preferably those in closed proximity, are interested to transmit simultaneously. Therefore, in this manuscript, we are going to present a hybrid slot allocation approach, which is specifically designed for those devices resided in neighborhood and are eager to communication concurrently with a common destination device, i.e., server. In the beginning, the k-mean clustering algorithm is used to group these devices into clusters where server is forced to collect data from devices deployed in the respective coverage areas. Thus, every server generates dedicated slots for active devices and an additional slot for server(s). Similarly, the proposed neighborhood-enabled time division multiple access (TDMA) has the flexibility of assigning multiple slots to a requesting device if available, which is needed in scenarios, such as detection of pest in the field. Additionally, a member device is allowed to migrate (if needed and possible) from one server's coverage region to another. Simulation results confirmed that the proposed approach is better than the existing algorithms (opportunistic TDMA, hybrid TDMA, and non-orthogonal multiple access), particularly in terms of bandwidth, end-to-end delay, and empty slot utilization. The proposed scheme has improved bandwidth and empty slot utilization, which are approximately 15% and 12%, respectively, whereas it has achieved approximately 94.89% utilization of the available slots which was previously 93.4%.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":"35 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141800602","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 : 2024-07-25DOI: 10.3389/fcomp.2024.1371052
Tarik Chakkour
In recent years, there has been a rising interest in potentially complex software and financial industries with applications in many engineering fields. With this rise comes a host of developing a usable and consistent Application Programming Interface (API). Prioritize designing and building the software ensures to enrich the platform and emphasize inventorying APIs. In this paper, we proposed a high-quality API to implement the continuous-in-time financial model. The existing discrete framework cannot be evaluated at any time period, involving drawbacks in operating the data structures. Then, the continuous framework is implemented based on the measure theory paradigm. Our proposal uses mathematical modeling, which consists of some objects as measures and fields. It is suitable to develop this API in C# to provide the requirement quality in programming language professionally. This also integrates demands, codes, and verification in the system development life cycle. The advantages are aimed at increasing the structuring and readability. The presented work provides an overview of the design, implementation, testing, and delivery aspects of the API, highlighting the importance of architecture, testing, and numerical choices. The article gives an overview of the API by describing the implementation concerning the data structures and algorithms. These algorithms are based on using the Task Parallel Library (TPL) that makes the API easier and more fruitful for data parallel to benefit from the advantages provided by the .NET Framework.
{"title":"High-quality implementation for a continuous-in-time financial API in C#","authors":"Tarik Chakkour","doi":"10.3389/fcomp.2024.1371052","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1371052","url":null,"abstract":"In recent years, there has been a rising interest in potentially complex software and financial industries with applications in many engineering fields. With this rise comes a host of developing a usable and consistent Application Programming Interface (API). Prioritize designing and building the software ensures to enrich the platform and emphasize inventorying APIs. In this paper, we proposed a high-quality API to implement the continuous-in-time financial model. The existing discrete framework cannot be evaluated at any time period, involving drawbacks in operating the data structures. Then, the continuous framework is implemented based on the measure theory paradigm. Our proposal uses mathematical modeling, which consists of some objects as measures and fields. It is suitable to develop this API in C# to provide the requirement quality in programming language professionally. This also integrates demands, codes, and verification in the system development life cycle. The advantages are aimed at increasing the structuring and readability. The presented work provides an overview of the design, implementation, testing, and delivery aspects of the API, highlighting the importance of architecture, testing, and numerical choices. The article gives an overview of the API by describing the implementation concerning the data structures and algorithms. These algorithms are based on using the Task Parallel Library (TPL) that makes the API easier and more fruitful for data parallel to benefit from the advantages provided by the .NET Framework.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":"30 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141803544","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 : 2024-07-23DOI: 10.3389/fcomp.2024.1454694
Eva Geurts, Gustavo Alberto Rovelo Ruiz, Kris Luyten, Philippe Palanque
{"title":"Editorial: HCI and worker well-being","authors":"Eva Geurts, Gustavo Alberto Rovelo Ruiz, Kris Luyten, Philippe Palanque","doi":"10.3389/fcomp.2024.1454694","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1454694","url":null,"abstract":"","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":"91 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141812375","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 : 2024-07-22DOI: 10.3389/fcomp.2024.1412458
Toyohisa Nakada, Motoki Miura
This study attempted to determine whether individuals possess programming aptitude solely based on keystroke information from typing games where participants type computer programs. The participants were students enrolled in university programming courses. The results indicated that using typing speed alone as an indicator achieved an accuracy of 0.71, while employing a custom machine learning model achieved an accuracy of 0.83. Additionally, it was found that individuals with programming aptitude tended to type the enter key relatively slower compared to other keys.
{"title":"Extracting typing game keystroke patterns as potential indicators of programming aptitude","authors":"Toyohisa Nakada, Motoki Miura","doi":"10.3389/fcomp.2024.1412458","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1412458","url":null,"abstract":"This study attempted to determine whether individuals possess programming aptitude solely based on keystroke information from typing games where participants type computer programs. The participants were students enrolled in university programming courses. The results indicated that using typing speed alone as an indicator achieved an accuracy of 0.71, while employing a custom machine learning model achieved an accuracy of 0.83. Additionally, it was found that individuals with programming aptitude tended to type the enter key relatively slower compared to other keys.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":"14 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141816204","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 : 2024-07-08DOI: 10.3389/fcomp.2024.1288552
Nadim Rana, Fathe Jeribi, Zeba Khan, Wagdi Alrawagfeh, Imed Ben Dhaou, Mohammad Haseebuddin, Mueen Uddin
The migration of business and scientific operations to the cloud and the surge in data from IoT devices have intensified the complexity of cloud resource scheduling. Ensuring efficient resource distribution in line with user-specified SLA and QoS demands novel scheduling solutions. This study scrutinizes contemporary Virtual Machine (VM) scheduling strategies, shedding light on the complexities and future prospects of VM design and aims to propel further research by highlighting existing obstacles and untapped potential in the ever-evolving realm of cloud and multi-access edge computing (MEC).Implementing a Systematic Literature Review (SLR), this research dissects VM scheduling techniques. A meticulous selection process distilled 67 seminal studies from an initial corpus of 722, spanning from 2008 to 2022. This critical filtration has been pivotal for grasping the developmental trajectory and current tendencies in VM scheduling practices.The in-depth examination of 67 studies on VM scheduling has produced a taxonomic breakdown into three principal methodologies: traditional, heuristic, and meta-heuristic. The review underscores a marked shift toward heuristic and meta-heuristic methods, reflecting their growing significance in the advancement of VM scheduling.Although VM scheduling has progressed markedly, the focus remains predominantly on metaheuristic and heuristic approaches. The analysis enlightens ongoing challenges and the direction of future developments, highlighting the necessity for persistent research and innovation in this sector.
{"title":"A systematic literature review on contemporary and future trends in virtual machine scheduling techniques in cloud and multi-access computing","authors":"Nadim Rana, Fathe Jeribi, Zeba Khan, Wagdi Alrawagfeh, Imed Ben Dhaou, Mohammad Haseebuddin, Mueen Uddin","doi":"10.3389/fcomp.2024.1288552","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1288552","url":null,"abstract":"The migration of business and scientific operations to the cloud and the surge in data from IoT devices have intensified the complexity of cloud resource scheduling. Ensuring efficient resource distribution in line with user-specified SLA and QoS demands novel scheduling solutions. This study scrutinizes contemporary Virtual Machine (VM) scheduling strategies, shedding light on the complexities and future prospects of VM design and aims to propel further research by highlighting existing obstacles and untapped potential in the ever-evolving realm of cloud and multi-access edge computing (MEC).Implementing a Systematic Literature Review (SLR), this research dissects VM scheduling techniques. A meticulous selection process distilled 67 seminal studies from an initial corpus of 722, spanning from 2008 to 2022. This critical filtration has been pivotal for grasping the developmental trajectory and current tendencies in VM scheduling practices.The in-depth examination of 67 studies on VM scheduling has produced a taxonomic breakdown into three principal methodologies: traditional, heuristic, and meta-heuristic. The review underscores a marked shift toward heuristic and meta-heuristic methods, reflecting their growing significance in the advancement of VM scheduling.Although VM scheduling has progressed markedly, the focus remains predominantly on metaheuristic and heuristic approaches. The analysis enlightens ongoing challenges and the direction of future developments, highlighting the necessity for persistent research and innovation in this sector.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":"119 34","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141666763","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 : 2024-07-04DOI: 10.3389/fcomp.2024.1381850
Ramireddy Nava Teja Reddy, M. Kavitha, G. S. Reddy, Amr H. Yousef, K. Aboras, Ahmed Emara, Ch. Rami Reddy
Various applications use asymmetric cryptography to secure communications between both parties, and it raises the main issue of generating vast amounts of computation and storage. Thus, elliptic curve cryptography (ECC) is a methodology that emerged to overcome this issue using its low computation and generation of small keys with its strong encryption strategy. ECC is becoming mandatory and used mostly for public key encryption protocols. ECC has expanded cumulative acceptance in practice due to the reduced bit magnitude of operands compared to RSA for safety level. Previously, protocols designed for ECC suggested calculation of scalar development and it was accomplished in finite fields as projective, affine, and Jacobian simulations of coordinates. Arithmetic operations in a limited area establish the core benefits of the ECC algorithm. Even though ECC generated an issue of complex key generation using its curve formation, to overcome this issue a hyperelliptic curve cryptosystems (HECC) is proposed in this study. HECC perform ECC in the Public Key Cryptography (PKC) domain. This study presented an optimization-based key generation and made a random selection of integers for encrypting the message. Selecting a prime number as the private key and multiplying it to the encrypted message to generate a public key is done. This encrypted message is mapped to the curve to check whether it satisfies the curve equation or not. Once an encrypted message is obtained, it is then sent to a second party for pursuing the message. On the side of the second party, a reverse process called decryption takes place. Thus, a secured transmission of data communication takes place. Implementing this algorithm in MATLAB resulted in 94% accuracy and an error of 6%, which was a higher performance ratio than previous methods.
{"title":"Mayfly optimistic hyperelliptic curve cryptosystem","authors":"Ramireddy Nava Teja Reddy, M. Kavitha, G. S. Reddy, Amr H. Yousef, K. Aboras, Ahmed Emara, Ch. Rami Reddy","doi":"10.3389/fcomp.2024.1381850","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1381850","url":null,"abstract":"Various applications use asymmetric cryptography to secure communications between both parties, and it raises the main issue of generating vast amounts of computation and storage. Thus, elliptic curve cryptography (ECC) is a methodology that emerged to overcome this issue using its low computation and generation of small keys with its strong encryption strategy. ECC is becoming mandatory and used mostly for public key encryption protocols. ECC has expanded cumulative acceptance in practice due to the reduced bit magnitude of operands compared to RSA for safety level. Previously, protocols designed for ECC suggested calculation of scalar development and it was accomplished in finite fields as projective, affine, and Jacobian simulations of coordinates. Arithmetic operations in a limited area establish the core benefits of the ECC algorithm. Even though ECC generated an issue of complex key generation using its curve formation, to overcome this issue a hyperelliptic curve cryptosystems (HECC) is proposed in this study. HECC perform ECC in the Public Key Cryptography (PKC) domain. This study presented an optimization-based key generation and made a random selection of integers for encrypting the message. Selecting a prime number as the private key and multiplying it to the encrypted message to generate a public key is done. This encrypted message is mapped to the curve to check whether it satisfies the curve equation or not. Once an encrypted message is obtained, it is then sent to a second party for pursuing the message. On the side of the second party, a reverse process called decryption takes place. Thus, a secured transmission of data communication takes place. Implementing this algorithm in MATLAB resulted in 94% accuracy and an error of 6%, which was a higher performance ratio than previous methods.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":" 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141678865","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 : 2024-07-03DOI: 10.3389/fcomp.2024.1378796
Pilar Terron-Lopez, M. Terrón-López, Guillermo Castilla-Cebrian
The potential impact of a video game is directly conditioned by its recognizability in the public conscience. But classifying video games in this manner can be a challenging endeavor. This paper emphasizes inconsistencies in recognition metrics and the absence of a unified system of classification. It approaches the problem through a twofold methodology involving a systematic literature review exploring existing classifications and genres, and an exploratory survey gathering data on spontaneously recognized video games in Spain. The study utilizes quantitative data to create three lists of video games—most played globally, most representative internationally, and most significant in the Spanish market. The findings reveal complexities in comparing video game data and underscore the importance of comprehensive research frameworks. The study contributes valuable insights into video game recognition dynamics among users, addresses the scarcity of comparative research in the gaming field, revealing the subjective impact of globally recognized video games and highlighting the possible relations between industry trends, spontaneous recognition, and consumer preferences.
{"title":"Spontaneous recognition of impactful video games: a user-centric classification framework","authors":"Pilar Terron-Lopez, M. Terrón-López, Guillermo Castilla-Cebrian","doi":"10.3389/fcomp.2024.1378796","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1378796","url":null,"abstract":"The potential impact of a video game is directly conditioned by its recognizability in the public conscience. But classifying video games in this manner can be a challenging endeavor. This paper emphasizes inconsistencies in recognition metrics and the absence of a unified system of classification. It approaches the problem through a twofold methodology involving a systematic literature review exploring existing classifications and genres, and an exploratory survey gathering data on spontaneously recognized video games in Spain. The study utilizes quantitative data to create three lists of video games—most played globally, most representative internationally, and most significant in the Spanish market. The findings reveal complexities in comparing video game data and underscore the importance of comprehensive research frameworks. The study contributes valuable insights into video game recognition dynamics among users, addresses the scarcity of comparative research in the gaming field, revealing the subjective impact of globally recognized video games and highlighting the possible relations between industry trends, spontaneous recognition, and consumer preferences.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141680378","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 : 2024-07-02DOI: 10.3389/fcomp.2024.1428013
M. A. Tamal, Md K. Islam, Touhid Bhuiyan, Abdus Sattar, Nayem Uddin Prince
The dynamic and sophisticated nature of phishing attacks, coupled with the relatively weak anti-phishing tools, has made phishing detection a pressing challenge. In light of this, new gaps have emerged in phishing detection, including the challenges and pitfalls of existing phishing detection techniques. To bridge these gaps, this study aims to develop a more robust, effective, sophisticated, and reliable solution for phishing detection through the optimal feature vectorization algorithm (OFVA) and supervised machine learning (SML) classifiers.Initially, the OFVA was utilized to extract the 41 optimal intra-URL features from a novel large dataset comprising 2,74,446 raw URLs (134,500 phishing and 139,946 legitimate URLs). Subsequently, data cleansing, curation, and dimensionality reduction were performed to remove outliers, handle missing values, and exclude less predictive features. To identify the optimal model, the study evaluated and compared 15 SML algorithms arising from different machine learning (ML) families, including Bayesian, nearest-neighbors, decision trees, neural networks, quadratic discriminant analysis, logistic regression, bagging, boosting, random forests, and ensembles. The evaluation was performed based on various metrics such as confusion matrix, accuracy, precision, recall, F-1 score, ROC curve, and precision-recall curve analysis. Furthermore, hyperparameter tuning (using Grid-search) and k-fold cross-validation were performed to optimize the detection accuracy.The findings indicate that random forests (RF) outperformed the other classifiers, achieving a greater accuracy rate of 97.52%, followed by 97.50% precision, and an AUC value of 97%. Finally, a more robust and lightweight anti-phishing model was introduced, which can serve as an effective tool for security experts, practitioners, and policymakers to combat phishing attacks.
{"title":"Unveiling suspicious phishing attacks: enhancing detection with an optimal feature vectorization algorithm and supervised machine learning","authors":"M. A. Tamal, Md K. Islam, Touhid Bhuiyan, Abdus Sattar, Nayem Uddin Prince","doi":"10.3389/fcomp.2024.1428013","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1428013","url":null,"abstract":"The dynamic and sophisticated nature of phishing attacks, coupled with the relatively weak anti-phishing tools, has made phishing detection a pressing challenge. In light of this, new gaps have emerged in phishing detection, including the challenges and pitfalls of existing phishing detection techniques. To bridge these gaps, this study aims to develop a more robust, effective, sophisticated, and reliable solution for phishing detection through the optimal feature vectorization algorithm (OFVA) and supervised machine learning (SML) classifiers.Initially, the OFVA was utilized to extract the 41 optimal intra-URL features from a novel large dataset comprising 2,74,446 raw URLs (134,500 phishing and 139,946 legitimate URLs). Subsequently, data cleansing, curation, and dimensionality reduction were performed to remove outliers, handle missing values, and exclude less predictive features. To identify the optimal model, the study evaluated and compared 15 SML algorithms arising from different machine learning (ML) families, including Bayesian, nearest-neighbors, decision trees, neural networks, quadratic discriminant analysis, logistic regression, bagging, boosting, random forests, and ensembles. The evaluation was performed based on various metrics such as confusion matrix, accuracy, precision, recall, F-1 score, ROC curve, and precision-recall curve analysis. Furthermore, hyperparameter tuning (using Grid-search) and k-fold cross-validation were performed to optimize the detection accuracy.The findings indicate that random forests (RF) outperformed the other classifiers, achieving a greater accuracy rate of 97.52%, followed by 97.50% precision, and an AUC value of 97%. Finally, a more robust and lightweight anti-phishing model was introduced, which can serve as an effective tool for security experts, practitioners, and policymakers to combat phishing attacks.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141686994","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}
The Internet of Things (IoT) proposes to transform human civilization so that it is smart, practical, and highly efficient, with enormous potential for commercial as well as social and environmental advantages. Reliability is one of the major problems that must be resolved to enable this revolutionary change. The reliability issues raised with specific supporting technologies for each tier according to the layered IoT reliability are initially described in this research. The research then offers a complete review and assessment of IoT reliability. In this paper, various types of reliability on the IoT have been analyzed with each layer of IoT to solve the issues of failure rates, latency, MTTF, and MTBF. Each parameter has a certain classification and perception as well as enhancement in efficiency, accuracy, precision, timeliness, and completeness. Reliability models provide efficient solutions for different IoT problems, which are mirrored in the proposed study and classified with four types of reliabilities. The field of IoT reliability exploration is still in its initial phases, despite a sizable research record. Furthermore, the recent case study of CHISS is elaborated with discovered behaviors including brand-new aspects such as the multifaceted nature of evolving IoT systems, research opportunities, and difficulties.
{"title":"Reliability on the Internet of Things with designing approach for exploratory analysis","authors":"Khushwant Singh, Mohit Yadav, Yudhvir Singh, Dheer Dhwaz Barak, Ashish Saini, Fernando Moreira","doi":"10.3389/fcomp.2024.1382347","DOIUrl":"https://doi.org/10.3389/fcomp.2024.1382347","url":null,"abstract":"The Internet of Things (IoT) proposes to transform human civilization so that it is smart, practical, and highly efficient, with enormous potential for commercial as well as social and environmental advantages. Reliability is one of the major problems that must be resolved to enable this revolutionary change. The reliability issues raised with specific supporting technologies for each tier according to the layered IoT reliability are initially described in this research. The research then offers a complete review and assessment of IoT reliability. In this paper, various types of reliability on the IoT have been analyzed with each layer of IoT to solve the issues of failure rates, latency, MTTF, and MTBF. Each parameter has a certain classification and perception as well as enhancement in efficiency, accuracy, precision, timeliness, and completeness. Reliability models provide efficient solutions for different IoT problems, which are mirrored in the proposed study and classified with four types of reliabilities. The field of IoT reliability exploration is still in its initial phases, despite a sizable research record. Furthermore, the recent case study of CHISS is elaborated with discovered behaviors including brand-new aspects such as the multifaceted nature of evolving IoT systems, research opportunities, and difficulties.","PeriodicalId":510141,"journal":{"name":"Frontiers in Computer Science","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141267837","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：