MD. JAMINUR ISLAM | Western Michigan University (original) (raw)
Uploads
Papers by MD. JAMINUR ISLAM
ACM Transactions on Cyber-Physical Systems
Modern smart cities need smart transportation solutions to quickly detect various traffic emergen... more Modern smart cities need smart transportation solutions to quickly detect various traffic emergencies and incidents in the city to avoid cascading traffic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traffic conditions on each road segment. In this paper, we first propose a scalable data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust ...
ACM TCPS, 2023
Modern smart cities need smart transportation solutions to quickly detect various traic emergenci... more Modern smart cities need smart transportation solutions to quickly detect various traic emergencies and incidents in the city to avoid cascading traic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traic conditions on each road segment. In this paper, we irst propose a scalable data-driven anomaly-based traic incident detection framework for a city-scale smart transportation system. Speciically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. Second, using cluster-level detection, we propose a folded Gaussian classiier to pinpoint the particular segment in a cluster where the incident happened in an automated manner. We perform extensive experimental validation using mobility data collected from four cities in Tennessee, compare with the state-of-the-art ML methods, to prove that our method can detect incidents within each cluster in real-time and outperforms known ML methods.
IEEE Access
Recently, Blockchain-based applications have become immensely popular because of limited reliance... more Recently, Blockchain-based applications have become immensely popular because of limited reliance on a single entity, unlike a centralized system. However, reaching a consensus among blockchain networks is a challenging and vital aspect of blockchain-based applications. There are various types of blockchain networks for different kinds of application scenarios. Among all of them, the consensus algorithm is the most crucial part of reaching an agreement in the complex blockchain network. Over the years, researchers have focused on dealing with the challenges like distributed computing, storage, transaction speed, security, validity, interoperability, and many more. However, only some of them are appropriate for all domains. Therefore, this paper presents an extensive study of different types of consensus protocols used in existing blockchain solutions with the strength and limitations of each algorithm. We also provide an inherent comparison among different algorithms to understand consensus protocol selection better. Moreover, we investigate operational and interoperability issues in existing blockchain-based applications to understand challenges and provide recommendations for future developers. INDEX TERMS Blockchain, consensus algorithm, interoperability, cross-chain transactions, architecture, operational issues, applications, research directions.
2022 ACM/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS)
Modern smart cities are focusing on smart transportation solutions to detect and mitigate the eff... more Modern smart cities are focusing on smart transportation solutions to detect and mitigate the effects of various traffic incidents in the city. To materialize this, roadside units and ambient transportation sensors are being deployed to collect vehicular data that provides real-time traffic monitoring. In this paper, we first propose a real-time data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. We perform extensive experimental validation using mobility data collected from the City of Nashville, Tennessee, and prove that the method can detect incidents within each cluster in real-time.
Proceedings of the 8th ACM on Cyber-Physical System Security Workshop
Anomaly-based attack detection methods are often used to detect data integrity or data falsificat... more Anomaly-based attack detection methods are often used to detect data integrity or data falsification attacks in advanced metering infrastructure (AMI) of smart grids. However, there is a lack of studies on the effect of data poisoning attacks against the anomaly based attack detectors that depend on some form of machine learning. In this paper, we introduce some data poisoning attack strategies against anomaly-based attack detectors in smart metering infrastructure and show its impact. Specifically, we propose a whitebox and black box approach to poisoning attacks. Then, we propose modifications to improve the robustness of previous anomaly detection algorithms by modifying certain design choices for learning the thresholds for the anomaly detector. Specifically, we offer theoretical insights and experimental proof to explain why and when they mitigate data poisoning. These design choices include both the regression type and the loss function choice. We measure attack mitigation performance with two NIST specified metrics for CPS systems in the test set using a real smart metering dataset. Finally, we offer recommendations on energy utility's best anomaly detector design choices under varying attack parameters. CCS CONCEPTS • Mathematics of computing → Regression analysis; • Computing methodologies → Machine learning; • Security and privacy; • Hardware → Smart grid;
ACM Transactions on Cyber-Physical Systems
Modern smart cities need smart transportation solutions to quickly detect various traffic emergen... more Modern smart cities need smart transportation solutions to quickly detect various traffic emergencies and incidents in the city to avoid cascading traffic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traffic conditions on each road segment. In this paper, we first propose a scalable data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust ...
ACM TCPS, 2023
Modern smart cities need smart transportation solutions to quickly detect various traic emergenci... more Modern smart cities need smart transportation solutions to quickly detect various traic emergencies and incidents in the city to avoid cascading traic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traic conditions on each road segment. In this paper, we irst propose a scalable data-driven anomaly-based traic incident detection framework for a city-scale smart transportation system. Speciically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. Second, using cluster-level detection, we propose a folded Gaussian classiier to pinpoint the particular segment in a cluster where the incident happened in an automated manner. We perform extensive experimental validation using mobility data collected from four cities in Tennessee, compare with the state-of-the-art ML methods, to prove that our method can detect incidents within each cluster in real-time and outperforms known ML methods.
IEEE Access
Recently, Blockchain-based applications have become immensely popular because of limited reliance... more Recently, Blockchain-based applications have become immensely popular because of limited reliance on a single entity, unlike a centralized system. However, reaching a consensus among blockchain networks is a challenging and vital aspect of blockchain-based applications. There are various types of blockchain networks for different kinds of application scenarios. Among all of them, the consensus algorithm is the most crucial part of reaching an agreement in the complex blockchain network. Over the years, researchers have focused on dealing with the challenges like distributed computing, storage, transaction speed, security, validity, interoperability, and many more. However, only some of them are appropriate for all domains. Therefore, this paper presents an extensive study of different types of consensus protocols used in existing blockchain solutions with the strength and limitations of each algorithm. We also provide an inherent comparison among different algorithms to understand consensus protocol selection better. Moreover, we investigate operational and interoperability issues in existing blockchain-based applications to understand challenges and provide recommendations for future developers. INDEX TERMS Blockchain, consensus algorithm, interoperability, cross-chain transactions, architecture, operational issues, applications, research directions.
2022 ACM/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS)
Modern smart cities are focusing on smart transportation solutions to detect and mitigate the eff... more Modern smart cities are focusing on smart transportation solutions to detect and mitigate the effects of various traffic incidents in the city. To materialize this, roadside units and ambient transportation sensors are being deployed to collect vehicular data that provides real-time traffic monitoring. In this paper, we first propose a real-time data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. We perform extensive experimental validation using mobility data collected from the City of Nashville, Tennessee, and prove that the method can detect incidents within each cluster in real-time.
Proceedings of the 8th ACM on Cyber-Physical System Security Workshop
Anomaly-based attack detection methods are often used to detect data integrity or data falsificat... more Anomaly-based attack detection methods are often used to detect data integrity or data falsification attacks in advanced metering infrastructure (AMI) of smart grids. However, there is a lack of studies on the effect of data poisoning attacks against the anomaly based attack detectors that depend on some form of machine learning. In this paper, we introduce some data poisoning attack strategies against anomaly-based attack detectors in smart metering infrastructure and show its impact. Specifically, we propose a whitebox and black box approach to poisoning attacks. Then, we propose modifications to improve the robustness of previous anomaly detection algorithms by modifying certain design choices for learning the thresholds for the anomaly detector. Specifically, we offer theoretical insights and experimental proof to explain why and when they mitigate data poisoning. These design choices include both the regression type and the loss function choice. We measure attack mitigation performance with two NIST specified metrics for CPS systems in the test set using a real smart metering dataset. Finally, we offer recommendations on energy utility's best anomaly detector design choices under varying attack parameters. CCS CONCEPTS • Mathematics of computing → Regression analysis; • Computing methodologies → Machine learning; • Security and privacy; • Hardware → Smart grid;