Ashraf Alkhresheh - Academia.edu (original) (raw)
Uploads
Papers by Ashraf Alkhresheh
2022 International Conference on Emerging Trends in Computing and Engineering Applications (ETCEA)
International Journal of Advanced Computer Science and Applications
Electricity theft-induced power loss is a pressing issue in both traditional and smart grid envir... more Electricity theft-induced power loss is a pressing issue in both traditional and smart grid environments. In smart grids, smart meters can be used to track power consumption behaviour and detect any suspicious activity. However, smart meter readings can be compromised by deploying intrusion tactics or launching cyber attacks. In this regard, machine learning models can be used to assess the daily consumption patterns of customers and detect potential electricity theft incidents. Whilst existing research efforts have extensively focused on batch learning algorithms, this paper investigates the use of online machine learning algorithms for electricity theft detection in smart grid environments, based on a recently proposed dataset. Several algorithms including Naive Bayes, K-nearest Neighbours, K-nearest Neighbours with self-adjusting memory, Hoeffding Tree, Extremely Fast Decision Tree, Adaptive Random Forest and Leveraging Bagging are considered. These algorithms are evaluated using an online machine learning platform considering both binary and multi-class theft detection scenarios. Evaluation metrics include prediction accuracy, precision, recall, F-1 score and kappa statistic. Evaluation results demonstrate the ability of the Leveraging Bagging algorithm with an Adaptive Random Forest base classifier to surpass all other algorithms in terms of all the considered metrics, for both binary and multi-class theft detection. Hence, it can be considered as a viable option for electricity theft detection in smart grid environments.
2020 International Wireless Communications and Mobile Computing (IWCMC), 2020
In the era of the Internet of Things (IoT), it has become possible for a set of smart devices to ... more In the era of the Internet of Things (IoT), it has become possible for a set of smart devices to collaborate autonomously and communicate seamlessly to achieve complex tasks that require a high degree of intelligence. Unlike traditional internet devices, a compromised IoT device can cause real-world damages. The severity of these damages increases dangerously in sensitive contexts especially when these devices are controlled by system insiders. Detecting abnormal access behaviors in such environments is quite challenging, due to frequent changes in the access contexts under which the IoT device can be accessed. In this paper, we propose an adaptive access control policy framework that dynamically refines the system access policies in response to changes in the device-to-device access behavior. We apply supervised machine learning to model and classify the device access behavior based on a real-life data set. We provide a use case scenario of a door locking system to validate our wor...
2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), 2019
Advancements and convergence in IoT enabling technologies along with ubiquitous connectivity have... more Advancements and convergence in IoT enabling technologies along with ubiquitous connectivity have led to the generation of new wave of smart services and applications based on real-time data access. The popularity of ubiquitous data access and accelerated adoption of these services pose significant challenges on user and data privacy. Thus, controlling access to such services in highly dynamic environments with continuously changing context becomes even more challenging. The wide adoption of IoT in our everyday life in many vital domains such as healthcare and military operations requires continuous and tight access control to prevent unauthorized and unintended access. A delay in making access decisions when context changes may result in consequences that cause harm and property damage. Therefore, continuity in access policy enforcement becomes a necessity in highly dynamic IoT environments for the entire access session not only at the time of request. This paper presents CAPE, a c...
In the near future, IoT ecosystems will enable billions of smart things to interconnect and commu... more In the near future, IoT ecosystems will enable billions of smart things to interconnect and communicate information about themselves and their physical environments. The high density of smart things in these environments allows for fine-grained data acquisition, enabling the development of advanced services and new kinds of applications ranging from wearable devices to air conditioners to fully automated cars. However, the dense and pervasive collection, processing and dissemination of data can unleash sensitive information about individuals, raising non-trivial security and privacy concerns. One solution for IoT security and privacy is to restrict access to sensitive data using access control and authorization techniques. Although many basic principles of standard access control models continue to apply, the high dynamic nature of IoT environments, resources limitation of IoT devices and vulnerability to physical and virtual attacks present unique challenges that render existing ac...
Data privacy becomes a primary impediment to the realization of the IoT vision. One approach to t... more Data privacy becomes a primary impediment to the realization of the IoT vision. One approach to the IoT security and privacy problem is to restrict access to sensitive data via access control and authorization models. Yet access context in IoT changes frequently raising the need for flexible and dynamic access control policies. Towards developing dynamic access control policies, context-based access control techniques are being investigated due to their robustness in assigning dynamic access permissions according to changes in context. In this paper, we propose to automate the generation of access control policies to overcome the inflexibility in traditional access policy specification techniques, and improve its adaptability to dynamic IoT environments. In our framework, we use context, attributes, and predication to describe the core access control elements. In response to access requests, our algorithm automatically produces conflict-free access control policies and makes the fin...
This paper aims at identifying the optimal Multicore processor configuration for cryptographic ap... more This paper aims at identifying the optimal Multicore processor configuration for cryptographic applications. The RSA encryption algorithm has been taken as a case study and a comprehensive design space exploration (DSE) has been performed to obtain the optimal processor configuration that can serve as either a standalone or a coprocessor for security applications. The DSE was based on four figures of merit that include: performance, power consumption, energy dissipation and lifetime reliability of the processor. A parallel version of the RSA algorithm has been implemented and used as an experimentation workload. Direct program execution and full-system simulation have been used to evaluate each candidate processor configuration based on the aforementioned figures of merit. Our analysis was based on commodity processors in order to come up with realistic optimal processor configuration in terms of its clock rate, number of cores, number of hardware threads, process technology and cac...
IEEE Internet of Things Journal
2022 International Conference on Emerging Trends in Computing and Engineering Applications (ETCEA)
International Journal of Advanced Computer Science and Applications
Electricity theft-induced power loss is a pressing issue in both traditional and smart grid envir... more Electricity theft-induced power loss is a pressing issue in both traditional and smart grid environments. In smart grids, smart meters can be used to track power consumption behaviour and detect any suspicious activity. However, smart meter readings can be compromised by deploying intrusion tactics or launching cyber attacks. In this regard, machine learning models can be used to assess the daily consumption patterns of customers and detect potential electricity theft incidents. Whilst existing research efforts have extensively focused on batch learning algorithms, this paper investigates the use of online machine learning algorithms for electricity theft detection in smart grid environments, based on a recently proposed dataset. Several algorithms including Naive Bayes, K-nearest Neighbours, K-nearest Neighbours with self-adjusting memory, Hoeffding Tree, Extremely Fast Decision Tree, Adaptive Random Forest and Leveraging Bagging are considered. These algorithms are evaluated using an online machine learning platform considering both binary and multi-class theft detection scenarios. Evaluation metrics include prediction accuracy, precision, recall, F-1 score and kappa statistic. Evaluation results demonstrate the ability of the Leveraging Bagging algorithm with an Adaptive Random Forest base classifier to surpass all other algorithms in terms of all the considered metrics, for both binary and multi-class theft detection. Hence, it can be considered as a viable option for electricity theft detection in smart grid environments.
2020 International Wireless Communications and Mobile Computing (IWCMC), 2020
In the era of the Internet of Things (IoT), it has become possible for a set of smart devices to ... more In the era of the Internet of Things (IoT), it has become possible for a set of smart devices to collaborate autonomously and communicate seamlessly to achieve complex tasks that require a high degree of intelligence. Unlike traditional internet devices, a compromised IoT device can cause real-world damages. The severity of these damages increases dangerously in sensitive contexts especially when these devices are controlled by system insiders. Detecting abnormal access behaviors in such environments is quite challenging, due to frequent changes in the access contexts under which the IoT device can be accessed. In this paper, we propose an adaptive access control policy framework that dynamically refines the system access policies in response to changes in the device-to-device access behavior. We apply supervised machine learning to model and classify the device access behavior based on a real-life data set. We provide a use case scenario of a door locking system to validate our wor...
2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), 2019
Advancements and convergence in IoT enabling technologies along with ubiquitous connectivity have... more Advancements and convergence in IoT enabling technologies along with ubiquitous connectivity have led to the generation of new wave of smart services and applications based on real-time data access. The popularity of ubiquitous data access and accelerated adoption of these services pose significant challenges on user and data privacy. Thus, controlling access to such services in highly dynamic environments with continuously changing context becomes even more challenging. The wide adoption of IoT in our everyday life in many vital domains such as healthcare and military operations requires continuous and tight access control to prevent unauthorized and unintended access. A delay in making access decisions when context changes may result in consequences that cause harm and property damage. Therefore, continuity in access policy enforcement becomes a necessity in highly dynamic IoT environments for the entire access session not only at the time of request. This paper presents CAPE, a c...
In the near future, IoT ecosystems will enable billions of smart things to interconnect and commu... more In the near future, IoT ecosystems will enable billions of smart things to interconnect and communicate information about themselves and their physical environments. The high density of smart things in these environments allows for fine-grained data acquisition, enabling the development of advanced services and new kinds of applications ranging from wearable devices to air conditioners to fully automated cars. However, the dense and pervasive collection, processing and dissemination of data can unleash sensitive information about individuals, raising non-trivial security and privacy concerns. One solution for IoT security and privacy is to restrict access to sensitive data using access control and authorization techniques. Although many basic principles of standard access control models continue to apply, the high dynamic nature of IoT environments, resources limitation of IoT devices and vulnerability to physical and virtual attacks present unique challenges that render existing ac...
Data privacy becomes a primary impediment to the realization of the IoT vision. One approach to t... more Data privacy becomes a primary impediment to the realization of the IoT vision. One approach to the IoT security and privacy problem is to restrict access to sensitive data via access control and authorization models. Yet access context in IoT changes frequently raising the need for flexible and dynamic access control policies. Towards developing dynamic access control policies, context-based access control techniques are being investigated due to their robustness in assigning dynamic access permissions according to changes in context. In this paper, we propose to automate the generation of access control policies to overcome the inflexibility in traditional access policy specification techniques, and improve its adaptability to dynamic IoT environments. In our framework, we use context, attributes, and predication to describe the core access control elements. In response to access requests, our algorithm automatically produces conflict-free access control policies and makes the fin...
This paper aims at identifying the optimal Multicore processor configuration for cryptographic ap... more This paper aims at identifying the optimal Multicore processor configuration for cryptographic applications. The RSA encryption algorithm has been taken as a case study and a comprehensive design space exploration (DSE) has been performed to obtain the optimal processor configuration that can serve as either a standalone or a coprocessor for security applications. The DSE was based on four figures of merit that include: performance, power consumption, energy dissipation and lifetime reliability of the processor. A parallel version of the RSA algorithm has been implemented and used as an experimentation workload. Direct program execution and full-system simulation have been used to evaluate each candidate processor configuration based on the aforementioned figures of merit. Our analysis was based on commodity processors in order to come up with realistic optimal processor configuration in terms of its clock rate, number of cores, number of hardware threads, process technology and cac...
IEEE Internet of Things Journal