Pub Date : 2024-03-18DOI: 10.1109/OJCS.2024.3378424
Usman Khalil;Mueen Uddin;Owais Ahmed Malik;Ong Wee Hong
The blueprint of the proposed Decentralized Smart City of Things (DSCoT) has been presented with smart contracts development and deployment for robust security of resources in the context of cyber-physical systems (CPS) for smart cities. Since non-fungibility provided by the ERC721 standard for the cyber-physical systems (CPSs) components such as the admin, user, and IoT-enabled smart device/s in literature is explicitly missing, the proposed DSCoT devised the functionality of identification and authentication of the assets. The proposed identification and authentication mechanism in cyber-physical systems (CPSs) employs smart contracts to generate an authentication access code based on extended non-fungible tokens (NFTs), which are used to authorize access to the corresponding assets. The evaluation and development of the extended NFT protocol for cyber-physical systems have been presented with the public and private blockchain deployments for evaluation comparison. The comparison demonstrated up to 96.69% promising results in terms of execution cost, efficiency, and time complexity compared to other proposed NFT-based solutions.
{"title":"A Novel NFT Solution for Assets Digitization and Authentication in Cyber-Physical Systems: Blueprint and Evaluation","authors":"Usman Khalil;Mueen Uddin;Owais Ahmed Malik;Ong Wee Hong","doi":"10.1109/OJCS.2024.3378424","DOIUrl":"10.1109/OJCS.2024.3378424","url":null,"abstract":"The blueprint of the proposed Decentralized Smart City of Things (DSCoT) has been presented with smart contracts development and deployment for robust security of resources in the context of cyber-physical systems (CPS) for smart cities. Since non-fungibility provided by the ERC721 standard for the cyber-physical systems (CPSs) components such as the admin, user, and IoT-enabled smart device/s in literature is explicitly missing, the proposed DSCoT devised the functionality of identification and authentication of the assets. The proposed identification and authentication mechanism in cyber-physical systems (CPSs) employs smart contracts to generate an authentication access code based on extended non-fungible tokens (NFTs), which are used to authorize access to the corresponding assets. The evaluation and development of the extended NFT protocol for cyber-physical systems have been presented with the public and private blockchain deployments for evaluation comparison. The comparison demonstrated up to 96.69% promising results in terms of execution cost, efficiency, and time complexity compared to other proposed NFT-based solutions.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"131-143"},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10474129","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140165630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-14DOI: 10.1109/OJCS.2024.3400696
Haoxuan Liu;Vasu Singh;Michał Filipiuk;Siva Kumar Sastry Hari
Vision Transformers are being increasingly deployed in safety-critical applications that demand high reliability. Ensuring the correct execution of these models in GPUs is critical, despite the potential for transient hardware errors. We propose a novel algorithm-based resilience framework called ALBERTA that allows us to perform end-to-end resilience analysis and protection of transformer-based architectures. First, our work develops an efficient process of computing and ranking the resilience of transformers layers. Due to the large size of transformer models, applying traditional network redundancy to a subset of the most vulnerable layers provides high error coverage albeit with impractically high overhead. We address this shortcoming by providing a software-directed, checksum-based error detection technique aimed at protecting the most vulnerable general matrix multiply (GEMM) layers in the transformer models that use either floating-point or integer arithmetic. Results show that our approach achieves over 99% coverage for errors (single bit-flip fault model) that result in a mismatch with $< $ 0.2% and $< $ 0.01% computation and memory overheads, respectively. Lastly, we present the applicability of our framework in various modern GPU architectures under different numerical precisions. We introduce an efficient self-correction mechanism for resolving erroneous detection with an average of less than 2% overhead per error.
{"title":"ALBERTA: ALgorithm-Based Error Resilience in Transformer Architectures","authors":"Haoxuan Liu;Vasu Singh;Michał Filipiuk;Siva Kumar Sastry Hari","doi":"10.1109/OJCS.2024.3400696","DOIUrl":"10.1109/OJCS.2024.3400696","url":null,"abstract":"Vision Transformers are being increasingly deployed in safety-critical applications that demand high reliability. Ensuring the correct execution of these models in GPUs is critical, despite the potential for transient hardware errors. We propose a novel algorithm-based resilience framework called ALBERTA that allows us to perform end-to-end resilience analysis and protection of transformer-based architectures. First, our work develops an efficient process of computing and ranking the resilience of transformers layers. Due to the large size of transformer models, applying traditional network redundancy to a subset of the most vulnerable layers provides high error coverage albeit with impractically high overhead. We address this shortcoming by providing a software-directed, checksum-based error detection technique aimed at protecting the most vulnerable general matrix multiply (GEMM) layers in the transformer models that use either floating-point or integer arithmetic. Results show that our approach achieves over 99% coverage for errors (single bit-flip fault model) that result in a mismatch with \u0000<inline-formula><tex-math>$< $</tex-math></inline-formula>\u00000.2% and \u0000<inline-formula><tex-math>$< $</tex-math></inline-formula>\u00000.01% computation and memory overheads, respectively. Lastly, we present the applicability of our framework in various modern GPU architectures under different numerical precisions. We introduce an efficient self-correction mechanism for resolving erroneous detection with an average of less than 2% overhead per error.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"85-96"},"PeriodicalIF":0.0,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10530530","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141060659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-09DOI: 10.1109/OJCS.2024.3398794
Syeda Tayyaba Bukhari;Muhammad Umar Janjua;Junaid Qadir
Blockchain technology enables users to control and record their cryptocurrency transactions through the use of digital wallets. As the use of blockchain technology and cryptocurrency wallets continues to grow in popularity, the potential for attacks on these wallets increases, as attackers seek to gain access to the large sums of cryptocurrency they contain. To mitigate these risks, it is important to conduct thorough security evaluations of wallets and implement strong protective measures. In recent years, there have been several incidents involving significant losses of cryptocurrency in crypto-wallets, and in this research, a comprehensive evaluation of seed phrase and password attack methods found in the published literature was conducted, and the topic was advanced by addressing the question of whether seed phrases are hackable. The research aims to use the elliptic-curve cryptography (ECC) encryption algorithm for storing the seed phrase online by encrypting the seed phrase and using the splitting technique to store the crypto wallet seed phrase. It was concluded that it is only possible to hack a seed phrase if a significant portion of it is already known, but even this would require a significant amount of time and computational power.
{"title":"Secure Storage of Crypto Wallet Seed Phrase Using ECC and Splitting Technique","authors":"Syeda Tayyaba Bukhari;Muhammad Umar Janjua;Junaid Qadir","doi":"10.1109/OJCS.2024.3398794","DOIUrl":"10.1109/OJCS.2024.3398794","url":null,"abstract":"Blockchain technology enables users to control and record their cryptocurrency transactions through the use of digital wallets. As the use of blockchain technology and cryptocurrency wallets continues to grow in popularity, the potential for attacks on these wallets increases, as attackers seek to gain access to the large sums of cryptocurrency they contain. To mitigate these risks, it is important to conduct thorough security evaluations of wallets and implement strong protective measures. In recent years, there have been several incidents involving significant losses of cryptocurrency in crypto-wallets, and in this research, a comprehensive evaluation of seed phrase and password attack methods found in the published literature was conducted, and the topic was advanced by addressing the question of whether seed phrases are hackable. The research aims to use the elliptic-curve cryptography (ECC) encryption algorithm for storing the seed phrase online by encrypting the seed phrase and using the splitting technique to store the crypto wallet seed phrase. It was concluded that it is only possible to hack a seed phrase if a significant portion of it is already known, but even this would require a significant amount of time and computational power.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"278-289"},"PeriodicalIF":0.0,"publicationDate":"2024-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10526424","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140928213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-08DOI: 10.1109/OJCS.2024.3398540
Petro Mushidi Tshakwanda;Sisay Tadesse Arzo;Michael Devetsikiotis
As 6G networks proliferate, they generate vast volumes of data and engage diverse devices, pushing the boundaries of traditional network management techniques. The limitations of these techniques underpin the need for a revolutionary shift towards AI/ML-based frameworks. This article introduces a transformative approach using our novel Speed-optimized LSTM (SP-LSTM) model, an embodiment of this crucial paradigm shift. We present a proactive strategy integrating predictive analytics and dynamic routing, underpinning efficient resource utilization and optimal network performance. This innovative, two-tiered system combines SP-LSTM networks and Reinforcement Learning (RL) for forecasting and dynamic routing. SP-LSTM models, boasting superior speed, predict potential network congestion, enabling preemptive action, while RL capitalizes on these forecasts to optimize routing and uphold network performance. This cutting-edge framework, driven by continuous learning and adaptation, mirrors the evolving nature of 6G networks, meeting the stringent requirements for ultra-low latency, ultra-reliability, and heterogeneity management. The expedited training and prediction times of SP-LSTM are game-changers, particularly in dynamic network environments where time is of the essence. Our work marks a significant stride towards integrating AI/ML in future network management, highlighting AI/ML's exceptional capacity to outperform conventional algorithms and drive innovative performance in 6G network management.
{"title":"Advancing 6G Network Performance: AI/ML Framework for Proactive Management and Dynamic Optimal Routing","authors":"Petro Mushidi Tshakwanda;Sisay Tadesse Arzo;Michael Devetsikiotis","doi":"10.1109/OJCS.2024.3398540","DOIUrl":"10.1109/OJCS.2024.3398540","url":null,"abstract":"As 6G networks proliferate, they generate vast volumes of data and engage diverse devices, pushing the boundaries of traditional network management techniques. The limitations of these techniques underpin the need for a revolutionary shift towards AI/ML-based frameworks. This article introduces a transformative approach using our novel Speed-optimized LSTM (SP-LSTM) model, an embodiment of this crucial paradigm shift. We present a proactive strategy integrating predictive analytics and dynamic routing, underpinning efficient resource utilization and optimal network performance. This innovative, two-tiered system combines SP-LSTM networks and Reinforcement Learning (RL) for forecasting and dynamic routing. SP-LSTM models, boasting superior speed, predict potential network congestion, enabling preemptive action, while RL capitalizes on these forecasts to optimize routing and uphold network performance. This cutting-edge framework, driven by continuous learning and adaptation, mirrors the evolving nature of 6G networks, meeting the stringent requirements for ultra-low latency, ultra-reliability, and heterogeneity management. The expedited training and prediction times of SP-LSTM are game-changers, particularly in dynamic network environments where time is of the essence. Our work marks a significant stride towards integrating AI/ML in future network management, highlighting AI/ML's exceptional capacity to outperform conventional algorithms and drive innovative performance in 6G network management.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"303-314"},"PeriodicalIF":0.0,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10522874","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140942005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gossip algorithms are often considered suitable for wireless sensor networks (WSNs) because of their simplicity, fault tolerance, and adaptability to network changes. They are based on the idea of distributed information dissemination, where each node in the network periodically sends its information to randomly selected neighbors, leading to a rapid spread of information throughout the network. This approach helps reduce the communication overhead and ensures robustness against node failures. They have been commonly employed in WSNs owing to their low communication overheads and scalability. The time required for every node in the network to converge to the average of its initial value is called the average time. The average time is defined in terms of the second-largest eigenvalue of a stochastic matrix. Thus, estimating and analyzing the average time required for large-scale WSNs is computationally complex. This study derives explicit expressions of average time for WSNs and studies the effect of various network parameters such as communication link failures, topology changes, long-range links, network dimension, node transmission range, and network size. Our theoretical expressions substantially reduced the computational complexity of computing the average time to $Oleft(n^{-3}right)$ . Furthermore, numerical results reveal that the long-range links and node transmission range of WSNs can significantly reduce average time, energy consumption, and absolute error for gossip algorithms.
{"title":"Performance Analysis of Gossip Algorithms for Large Scale Wireless Sensor Networks","authors":"Sateeshkrishna Dhuli;Fouzul Atik;Anamika Chhabra;Prem Singh;Linga Reddy Cenkeramaddi","doi":"10.1109/OJCS.2024.3397345","DOIUrl":"10.1109/OJCS.2024.3397345","url":null,"abstract":"Gossip algorithms are often considered suitable for wireless sensor networks (WSNs) because of their simplicity, fault tolerance, and adaptability to network changes. They are based on the idea of distributed information dissemination, where each node in the network periodically sends its information to randomly selected neighbors, leading to a rapid spread of information throughout the network. This approach helps reduce the communication overhead and ensures robustness against node failures. They have been commonly employed in WSNs owing to their low communication overheads and scalability. The time required for every node in the network to converge to the average of its initial value is called the average time. The average time is defined in terms of the second-largest eigenvalue of a stochastic matrix. Thus, estimating and analyzing the average time required for large-scale WSNs is computationally complex. This study derives explicit expressions of average time for WSNs and studies the effect of various network parameters such as communication link failures, topology changes, long-range links, network dimension, node transmission range, and network size. Our theoretical expressions substantially reduced the computational complexity of computing the average time to \u0000<inline-formula><tex-math>$Oleft(n^{-3}right)$</tex-math></inline-formula>\u0000. Furthermore, numerical results reveal that the long-range links and node transmission range of WSNs can significantly reduce average time, energy consumption, and absolute error for gossip algorithms.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"290-302"},"PeriodicalIF":0.0,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10521818","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140928391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-07DOI: 10.1109/OJCS.2024.3397307
Mohammad Wazid;Ashok Kumar Das;Youngho Park
Quantum cryptography has the potential to secure the infrastructures that are vulnerable to various attacks, like classical attacks, including quantum-related attacks. Therefore, quantum cryptography seems to be a promising technology for the future secure online infrastructures and applications, like blockchain-based frameworks. In this article, we propose a generic quantum blockchain-envisioned security framework for an Internet of Things (IoT) environment. We then discuss some potential applications of the proposed framework. We also highlight the security advantages of quantum cryptography-based systems. We explain the working of blockchain, applications of blockchain, types of blockchain, the structure of blockchain, the structure of blockchain in a classical blockchain, and the structure of a block in a quantum blockchain context. Next, the adverse effects of quantum computing on the security of blockchain-based frameworks are highlighted. Furthermore, the comparisons of quantum cryptography-based security schemes, like quantum key distribution, quantum digital signature, and quantum hashing schemes, are provided. Finally, some future research directions related to the designed generic quantum blockchain-envisioned security framework for IoT are provided.
{"title":"Generic Quantum Blockchain-Envisioned Security Framework for IoT Environment: Architecture, Security Benefits and Future Research","authors":"Mohammad Wazid;Ashok Kumar Das;Youngho Park","doi":"10.1109/OJCS.2024.3397307","DOIUrl":"10.1109/OJCS.2024.3397307","url":null,"abstract":"Quantum cryptography has the potential to secure the infrastructures that are vulnerable to various attacks, like classical attacks, including quantum-related attacks. Therefore, quantum cryptography seems to be a promising technology for the future secure online infrastructures and applications, like blockchain-based frameworks. In this article, we propose a generic quantum blockchain-envisioned security framework for an Internet of Things (IoT) environment. We then discuss some potential applications of the proposed framework. We also highlight the security advantages of quantum cryptography-based systems. We explain the working of blockchain, applications of blockchain, types of blockchain, the structure of blockchain, the structure of blockchain in a classical blockchain, and the structure of a block in a quantum blockchain context. Next, the adverse effects of quantum computing on the security of blockchain-based frameworks are highlighted. Furthermore, the comparisons of quantum cryptography-based security schemes, like quantum key distribution, quantum digital signature, and quantum hashing schemes, are provided. Finally, some future research directions related to the designed generic quantum blockchain-envisioned security framework for IoT are provided.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"248-267"},"PeriodicalIF":0.0,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10521804","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140927997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-02DOI: 10.1109/OJCS.2024.3396344
Christos Chronis;Iraklis Varlamis;Yassine Himeur;Aya N. Sayed;Tamim M. AL-Hasan;Armstrong Nhlabatsi;Faycal Bensaali;George Dimitrakopoulos
In the age of information overload, recommender systems have emerged as essential tools, assisting users in decision-making processes by offering personalized suggestions. However, their effectiveness is contingent on the availability of large amounts of user data, raising significant privacy and security concerns. This review article presents an extended analysis of recommender systems, elucidating their importance and the growing apprehensions regarding privacy and data security. Federated Learning (FL), a privacy-preserving machine learning approach, is introduced as a potential solution to these challenges. Consequently, the potential benefits and implications of integrating FL with recommender systems are explored and an overview of FL, its types, and key components, are provided. Further, the privacy-preserving techniques inherent to FL are discussed, demonstrating how they contribute to secure recommender systems. By illustrating case studies and significant research contributions, the article showcases the practical feasibility and benefits of combining FL with recommender systems. Despite the promising benefits, challenges, and limitations exist in the practical deployment of FL in recommender systems. This review outlines these hurdles, bringing to light the security considerations crucial in this context and offering a balanced perspective. In conclusion, the article signifies the potential of FL in transforming recommender systems, paving the path for future research directions in this intersection of technologies.
{"title":"A Survey on the use of Federated Learning in Privacy-Preserving Recommender Systems","authors":"Christos Chronis;Iraklis Varlamis;Yassine Himeur;Aya N. Sayed;Tamim M. AL-Hasan;Armstrong Nhlabatsi;Faycal Bensaali;George Dimitrakopoulos","doi":"10.1109/OJCS.2024.3396344","DOIUrl":"10.1109/OJCS.2024.3396344","url":null,"abstract":"In the age of information overload, recommender systems have emerged as essential tools, assisting users in decision-making processes by offering personalized suggestions. However, their effectiveness is contingent on the availability of large amounts of user data, raising significant privacy and security concerns. This review article presents an extended analysis of recommender systems, elucidating their importance and the growing apprehensions regarding privacy and data security. Federated Learning (FL), a privacy-preserving machine learning approach, is introduced as a potential solution to these challenges. Consequently, the potential benefits and implications of integrating FL with recommender systems are explored and an overview of FL, its types, and key components, are provided. Further, the privacy-preserving techniques inherent to FL are discussed, demonstrating how they contribute to secure recommender systems. By illustrating case studies and significant research contributions, the article showcases the practical feasibility and benefits of combining FL with recommender systems. Despite the promising benefits, challenges, and limitations exist in the practical deployment of FL in recommender systems. This review outlines these hurdles, bringing to light the security considerations crucial in this context and offering a balanced perspective. In conclusion, the article signifies the potential of FL in transforming recommender systems, paving the path for future research directions in this intersection of technologies.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"227-247"},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517657","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140840647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-28DOI: 10.1109/OJCS.2024.3370971
Abu Saleh Musa Miah;Md. Al Mehedi Hasan;Yoichi Tomioka;Jungpil Shin
Hand gesture-based Sign Language Recognition (SLR) serves as a crucial communication bridge between hard of hearing and non-deaf individuals. The absence of a universal sign language (SL) leads to diverse nationalities having various cultural SLs, such as Korean, American, and Japanese sign language. Existing SLR systems perform well for their cultural SL but may struggle with other or multi-cultural sign languages (McSL). To address these challenges, this paper introduces a novel end-to-end SLR system called GmTC, designed to translate McSL into equivalent text for enhanced understanding. Here, we employed a Graph and General deep-learning network as two stream modules to extract effective features. In the first stream, produce a graph-based feature by taking advantage of the superpixel values and the graph convolutional network (GCN), aiming to extract distance-based complex relationship features among the superpixel. In the second stream, we extracted long-range and short-range dependency features using attention-based contextual information that passes through multi-stage, multi-head self-attention (MHSA), and CNN modules. Combining these features generates final features that feed into the classification module. Extensive experiments with five culture SL datasets with high-performance accuracy compared to existing state-of-the-art models in individual domains affirming superiority and generalizability.
{"title":"Hand Gesture Recognition for Multi-Culture Sign Language Using Graph and General Deep Learning Network","authors":"Abu Saleh Musa Miah;Md. Al Mehedi Hasan;Yoichi Tomioka;Jungpil Shin","doi":"10.1109/OJCS.2024.3370971","DOIUrl":"10.1109/OJCS.2024.3370971","url":null,"abstract":"Hand gesture-based Sign Language Recognition (SLR) serves as a crucial communication bridge between hard of hearing and non-deaf individuals. The absence of a universal sign language (SL) leads to diverse nationalities having various cultural SLs, such as Korean, American, and Japanese sign language. Existing SLR systems perform well for their cultural SL but may struggle with other or multi-cultural sign languages (McSL). To address these challenges, this paper introduces a novel end-to-end SLR system called GmTC, designed to translate McSL into equivalent text for enhanced understanding. Here, we employed a Graph and General deep-learning network as two stream modules to extract effective features. In the first stream, produce a graph-based feature by taking advantage of the superpixel values and the graph convolutional network (GCN), aiming to extract distance-based complex relationship features among the superpixel. In the second stream, we extracted long-range and short-range dependency features using attention-based contextual information that passes through multi-stage, multi-head self-attention (MHSA), and CNN modules. Combining these features generates final features that feed into the classification module. Extensive experiments with five culture SL datasets with high-performance accuracy compared to existing state-of-the-art models in individual domains affirming superiority and generalizability.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"144-155"},"PeriodicalIF":0.0,"publicationDate":"2024-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10452793","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140008733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-27DOI: 10.1109/OJCS.2024.3370603
Yongrong Huang;Huiqing Wang;Zhide Chen;Chen Feng;Kexin Zhu;Xu Yang;Wencheng Yang
Cryptocurrency, a novel digital asset within the blockchain technology ecosystem, has recently garnered significant attention in the investment world. Despite its growing popularity, the inherent volatility and instability of cryptocurrency investments necessitate a thorough risk evaluation. This study utilizes the Autoregressive Moving Average (ARMA) model combined with the Generalized Autoregressive Conditionally Heteroscedastic (GARCH) model to analyze the volatility of three major cryptocurrencies—Bitcoin (BTC), Ethereum (ETH), and Binance Coin (BNB)—over a period from January 1, 2017, to October 29, 2022. The dataset comprises daily closing prices, offering a comprehensive view of the market's fluctuations. Our analysis revealed that the value-at-risk (VaR) curves for these cryptocurrencies demonstrate significant volatility, encompassing a broad spectrum of returns. The overall risk profile is relatively high, with ETH exhibiting the highest risk, followed by BTC and BNB. The ARMA-GARCH-VaR model has proven effective in quantifying and assessing the market risks associated with cryptocurrencies, providing valuable insights for investors and policymakers in navigating the complex landscape of digital assets.
{"title":"Evaluating Cryptocurrency Market Risk on the Blockchain: An Empirical Study Using the ARMA-GARCH-VaR Model","authors":"Yongrong Huang;Huiqing Wang;Zhide Chen;Chen Feng;Kexin Zhu;Xu Yang;Wencheng Yang","doi":"10.1109/OJCS.2024.3370603","DOIUrl":"10.1109/OJCS.2024.3370603","url":null,"abstract":"Cryptocurrency, a novel digital asset within the blockchain technology ecosystem, has recently garnered significant attention in the investment world. Despite its growing popularity, the inherent volatility and instability of cryptocurrency investments necessitate a thorough risk evaluation. This study utilizes the Autoregressive Moving Average (ARMA) model combined with the Generalized Autoregressive Conditionally Heteroscedastic (GARCH) model to analyze the volatility of three major cryptocurrencies—Bitcoin (BTC), Ethereum (ETH), and Binance Coin (BNB)—over a period from January 1, 2017, to October 29, 2022. The dataset comprises daily closing prices, offering a comprehensive view of the market's fluctuations. Our analysis revealed that the value-at-risk (VaR) curves for these cryptocurrencies demonstrate significant volatility, encompassing a broad spectrum of returns. The overall risk profile is relatively high, with ETH exhibiting the highest risk, followed by BTC and BNB. The ARMA-GARCH-VaR model has proven effective in quantifying and assessing the market risks associated with cryptocurrencies, providing valuable insights for investors and policymakers in navigating the complex landscape of digital assets.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"83-94"},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10449426","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139987737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pirated software is an attractive choice for cybercriminals seeking to spread malicious software, known as malware. This paper attempts to quantify the occurrence of malware concealed within pirated software. We collected samples of pirated software from various sources from Southeast Asian countries, including hard disk drives, optical discs purchased in eight different countries, and online platforms using peer-to-peer services. Our dataset comprises a total of 750 pirated software samples. To analyze these samples, we employed seven distinct antivirus (AV) engines. The malware identified by the AV engines was classified into four categories: adware, Trojans, viruses, and a miscellaneous category termed others. Our findings reveal that adware and Trojans are the most prevalent types of malware, with average infection rates of 34% and 35%, respectively, among our pirated software samples. Notably, our evaluation of AV detection performance highlights variations in sensitivity, ranging from a high of 132% to a low of 30% across all AV engines. Furthermore, upon installing pirated software, the most adversely affected operating system settings are the firewall and user account control configurations. Given the potential for malware to steal information or create malicious backdoors, its high prevalence within pirated software poses a substantial security risk to end users.
{"title":"Unveiling the Connection Between Malware and Pirated Software in Southeast Asian Countries: A Case Study","authors":"Asif Iqbal;Muhammad Naveed Aman;Ramkumar Rejendran;Biplab Sikdar","doi":"10.1109/OJCS.2024.3364576","DOIUrl":"https://doi.org/10.1109/OJCS.2024.3364576","url":null,"abstract":"Pirated software is an attractive choice for cybercriminals seeking to spread malicious software, known as malware. This paper attempts to quantify the occurrence of malware concealed within pirated software. We collected samples of pirated software from various sources from Southeast Asian countries, including hard disk drives, optical discs purchased in eight different countries, and online platforms using peer-to-peer services. Our dataset comprises a total of 750 pirated software samples. To analyze these samples, we employed seven distinct antivirus (AV) engines. The malware identified by the AV engines was classified into four categories: adware, Trojans, viruses, and a miscellaneous category termed others. Our findings reveal that adware and Trojans are the most prevalent types of malware, with average infection rates of 34% and 35%, respectively, among our pirated software samples. Notably, our evaluation of AV detection performance highlights variations in sensitivity, ranging from a high of 132% to a low of 30% across all AV engines. Furthermore, upon installing pirated software, the most adversely affected operating system settings are the firewall and user account control configurations. Given the potential for malware to steal information or create malicious backdoors, its high prevalence within pirated software poses a substantial security risk to end users.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"5 ","pages":"62-72"},"PeriodicalIF":0.0,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10430375","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139937097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：