Visualizing convolution as a series of element-wise (Hadamard) product operations between the data matrix and a set of expanded kernels
Abstract:
In Advanced Metering Infrastructure (AMI) networks, Smart Meters (SMs), are installed at consumers’ houses, provide electric utilities with fine-grained power consumption...Show MoreMetadata
Abstract:
In Advanced Metering Infrastructure (AMI) networks, Smart Meters (SMs), are installed at consumers’ houses, provide electric utilities with fine-grained power consumption data necessary for accurate billing, load monitoring, and energy management. However, utility companies are still subjected to electricity theft cyber-attacks in which fraudulent consumers may manipulate their reported readings and hence reduce their bills. Several ML-based electricity theft detectors have been proposed in the literature, however, they either do not capture well the deeper periodicity and temporal features in energy consumption data or violate consumers’ privacy by running these models over unencrypted power consumption data. To address these challenges, we propose in this paper a Conv-LSTM-based detector that integrates a 2-D Convolutional Neural Network (CNN) model with a Long Short-Term Memory (LSTM) network to significantly improve the model’s functionality and detection accuracy, specifically addressing the inherent periodicity and temporal dependencies in electricity consumption data. Moreover, to run the proposed model over encrypted 2D data and preserve consumers’ privacy, we designed a novel lightweight Inner Product Functional Encryption (IPFE) scheme that allows SMs to send their encrypted power consumption data to the Electric Utility (EU) which can securely compute the first feature map of the first convolutional layer of the Conv-LSTM detector while preserving consumer privacy. Our analysis and experiments demonstrate that our scheme is secure and efficiently detecting fraudulent consumers with minimal overhead. In specific, our model achieves a Detection Rate (DR) of 92.95%, a False Alarm Rate (FAR) of 3.68%, and a High Detection (HD) rate of 89.27%, resulting in an overall Accuracy (ACC) of 94.65%. Moreover, our scheme achieves high Precision (PR) at 98.80% and a robust Area Under the Curve (AUC) value of 98.50%. These results highlight the effectiveness of our appr...
Visualizing convolution as a series of element-wise (Hadamard) product operations between the data matrix and a set of expanded kernels
Published in: IEEE Access ( Volume: 12)
Funding Agency:
Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL, USA
Johnson Anin received the B.S. degree in electrical and electronic engineering from the University of Mines and Technology, Ghana, in 2017, the M.S. degree in electronics engineering from Norfolk State University, Norfolk, VA, USA, in 2020, and the Ph.D. degree in electrical and computer engineering from The University of Alabama (UA), Tuscaloosa, AL, USA, in August 2024. He is an Instructor with the Department of Physics...Show More
Johnson Anin received the B.S. degree in electrical and electronic engineering from the University of Mines and Technology, Ghana, in 2017, the M.S. degree in electronics engineering from Norfolk State University, Norfolk, VA, USA, in 2020, and the Ph.D. degree in electrical and computer engineering from The University of Alabama (UA), Tuscaloosa, AL, USA, in August 2024. He is an Instructor with the Department of Physics...View more
Department of Computer Science, The University of Alabama, Tuscaloosa, AL, USA
Muhammad Jahanzeb Khan received the bachelor’s degree in computer science from the NFC Institute of Engineering and Technology, Pakistan, the master’s degree in computer science from the University of Nevada Reno, Reno, NV, USA, and the master’s degree in software engineering from Shanghai Jiao Tong University, China. He is currently pursuing the Ph.D. degree with The University of Alabama, Tuscaloosa, with a focus on AI,...Show More
Muhammad Jahanzeb Khan received the bachelor’s degree in computer science from the NFC Institute of Engineering and Technology, Pakistan, the master’s degree in computer science from the University of Nevada Reno, Reno, NV, USA, and the master’s degree in software engineering from Shanghai Jiao Tong University, China. He is currently pursuing the Ph.D. degree with The University of Alabama, Tuscaloosa, with a focus on AI,...View more
Department of Computer Science, Tennessee Tech University, Cookeville, TN, USA
Omar Abdelsalam received the bachelor’s degree in computer science with a focus on data science and artificial intelligence, along with a minor in mathematics from Tennessee Technological University (TNTech), in 2024, where he is currently pursuing the Ph.D. degree in large language models. During his undergraduate years, he engaged in extensive research and internships, including a notable research experience for undergr...Show More
Omar Abdelsalam received the bachelor’s degree in computer science with a focus on data science and artificial intelligence, along with a minor in mathematics from Tennessee Technological University (TNTech), in 2024, where he is currently pursuing the Ph.D. degree in large language models. During his undergraduate years, he engaged in extensive research and internships, including a notable research experience for undergr...View more
Electrical and Computer Engineering, University of North Carolina A&T, Greensboro, NC, USA
Mahmoud Nabil (Senior Member, IEEE) received the B.S. and M.S. degrees (Hons.) in computer engineering from Cairo University, Egypt, in 2012 and 2016, respectively, and the Ph.D. degree in electrical and computer engineering from Tennessee Tech University, Cookeville, TN, USA, in August 2019. He is an Associate Professor with the Department of Electrical and Computer Engineering, North Carolina A&T State University. He is...Show More
Mahmoud Nabil (Senior Member, IEEE) received the B.S. and M.S. degrees (Hons.) in computer engineering from Cairo University, Egypt, in 2012 and 2016, respectively, and the Ph.D. degree in electrical and computer engineering from Tennessee Tech University, Cookeville, TN, USA, in August 2019. He is an Associate Professor with the Department of Electrical and Computer Engineering, North Carolina A&T State University. He is...View more
Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL, USA
Fei Hu (Member, IEEE) received the first Ph.D. degree in signal processing from Tongji University, Shanghai, China, in 1999, and the second Ph.D. degree in electrical and computer engineering from Clarkson University, New York, NY, USA, in 2002. He is currently a Professor with the Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL, USA. His research has been supported by U.S. NSF...Show More
Fei Hu (Member, IEEE) received the first Ph.D. degree in signal processing from Tongji University, Shanghai, China, in 1999, and the second Ph.D. degree in electrical and computer engineering from Clarkson University, New York, NY, USA, in 2002. He is currently a Professor with the Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL, USA. His research has been supported by U.S. NSF...View more
Department of Computer Science, The University of Alabama, Tuscaloosa, AL, USA
Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Banha, Egypt
Ahmad Alsharif (Senior Member, IEEE) received the B.Sc. and M.Sc. degrees (Hons.) in electrical engineering from Benha University, Cairo, Egypt, in 2009 and 2015, respectively, and the Ph.D. degree in electrical and computer engineering from Tennessee Tech University, Cookeville, TN, USA, in May 2019. Currently, he is an Assistant Professor with The University of Alabama, Tuscaloosa, AL, USA. He also holds the position of...Show More
Ahmad Alsharif (Senior Member, IEEE) received the B.Sc. and M.Sc. degrees (Hons.) in electrical engineering from Benha University, Cairo, Egypt, in 2009 and 2015, respectively, and the Ph.D. degree in electrical and computer engineering from Tennessee Tech University, Cookeville, TN, USA, in May 2019. Currently, he is an Assistant Professor with The University of Alabama, Tuscaloosa, AL, USA. He also holds the position of...View more
Contents Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL, USA
Johnson Anin received the B.S. degree in electrical and electronic engineering from the University of Mines and Technology, Ghana, in 2017, the M.S. degree in electronics engineering from Norfolk State University, Norfolk, VA, USA, in 2020, and the Ph.D. degree in electrical and computer engineering from The University of Alabama (UA), Tuscaloosa, AL, USA, in August 2024. He is an Instructor with the Department of Physics & Astronomy and the Department of Electrical Engineering, UA. His research interests include security and privacy in smart grids, machine/deep learning, hardware, and software engineering.
Johnson Anin received the B.S. degree in electrical and electronic engineering from the University of Mines and Technology, Ghana, in 2017, the M.S. degree in electronics engineering from Norfolk State University, Norfolk, VA, USA, in 2020, and the Ph.D. degree in electrical and computer engineering from The University of Alabama (UA), Tuscaloosa, AL, USA, in August 2024. He is an Instructor with the Department of Physics & Astronomy and the Department of Electrical Engineering, UA. His research interests include security and privacy in smart grids, machine/deep learning, hardware, and software engineering.View more
Department of Computer Science, The University of Alabama, Tuscaloosa, AL, USA
Muhammad Jahanzeb Khan received the bachelor’s degree in computer science from the NFC Institute of Engineering and Technology, Pakistan, the master’s degree in computer science from the University of Nevada Reno, Reno, NV, USA, and the master’s degree in software engineering from Shanghai Jiao Tong University, China. He is currently pursuing the Ph.D. degree with The University of Alabama, Tuscaloosa, with a focus on AI, federated learning, and privacy preservation. He is also a Computer Science Scholar. His research interests include deeply rooted in leveraging AI for societal benefit, with notable contributions to federated learning and privacy-preserving technologies. He actively engages in the Linux community, demonstrating his passion for open-source initiatives and collaborative innovation.
Muhammad Jahanzeb Khan received the bachelor’s degree in computer science from the NFC Institute of Engineering and Technology, Pakistan, the master’s degree in computer science from the University of Nevada Reno, Reno, NV, USA, and the master’s degree in software engineering from Shanghai Jiao Tong University, China. He is currently pursuing the Ph.D. degree with The University of Alabama, Tuscaloosa, with a focus on AI, federated learning, and privacy preservation. He is also a Computer Science Scholar. His research interests include deeply rooted in leveraging AI for societal benefit, with notable contributions to federated learning and privacy-preserving technologies. He actively engages in the Linux community, demonstrating his passion for open-source initiatives and collaborative innovation.View more
Department of Computer Science, Tennessee Tech University, Cookeville, TN, USA
Omar Abdelsalam received the bachelor’s degree in computer science with a focus on data science and artificial intelligence, along with a minor in mathematics from Tennessee Technological University (TNTech), in 2024, where he is currently pursuing the Ph.D. degree in large language models. During his undergraduate years, he engaged in extensive research and internships, including a notable research experience for undergraduates (REU) with The University of Alabama, where he worked on building encryption schemes and deep learning techniques to enhance the security of machine learning models. He has co-authored several publications in major IEEE conferences and journals, such as the IEEE INFOCOM Conference and IEEE Transactions on Neural Networks and Learning Systems. His research interests include large language models, reinforcement learning, and the security of machine learning models. He has also been active in academic and professional communities, serving as the Vice President for the MSA Students’ Association at TNTech and holding multiple leadership positions.
Omar Abdelsalam received the bachelor’s degree in computer science with a focus on data science and artificial intelligence, along with a minor in mathematics from Tennessee Technological University (TNTech), in 2024, where he is currently pursuing the Ph.D. degree in large language models. During his undergraduate years, he engaged in extensive research and internships, including a notable research experience for undergraduates (REU) with The University of Alabama, where he worked on building encryption schemes and deep learning techniques to enhance the security of machine learning models. He has co-authored several publications in major IEEE conferences and journals, such as the IEEE INFOCOM Conference and IEEE Transactions on Neural Networks and Learning Systems. His research interests include large language models, reinforcement learning, and the security of machine learning models. He has also been active in academic and professional communities, serving as the Vice President for the MSA Students’ Association at TNTech and holding multiple leadership positions.View more
Electrical and Computer Engineering, University of North Carolina A&T, Greensboro, NC, USA
Mahmoud Nabil (Senior Member, IEEE) received the B.S. and M.S. degrees (Hons.) in computer engineering from Cairo University, Egypt, in 2012 and 2016, respectively, and the Ph.D. degree in electrical and computer engineering from Tennessee Tech University, Cookeville, TN, USA, in August 2019. He is an Associate Professor with the Department of Electrical and Computer Engineering, North Carolina A&T State University. He is an accomplished Researcher. He has received significant funding for his research projects from esteemed national agencies and organizations, including the National Science Foundation (NSF), the Department of Transportation (DOT), the Air Force Research Laboratory (AFRL), NASA, Intel, Cisco, and Lockheed Martin. He has authored or co-authored several publications in prestigious venues. His research has been published in renowned journals, such as IEEE Internet of Things, IEEE Transactions of Dependable and Secure Computing, IEEE Transactions on Human-Machine Systems, and IEEE Transactions of Mobile Computing. He has also contributed to leading conferences, including the International Conference on Communication, International Conference on Pattern Recognition, and International Conference on Wireless Communication. With diverse research interests, his areas of expertise include security and privacy in unmanned aerial systems, smart grids, machine learning applications, vehicular ad hoc networks, and blockchain applications.
Mahmoud Nabil (Senior Member, IEEE) received the B.S. and M.S. degrees (Hons.) in computer engineering from Cairo University, Egypt, in 2012 and 2016, respectively, and the Ph.D. degree in electrical and computer engineering from Tennessee Tech University, Cookeville, TN, USA, in August 2019. He is an Associate Professor with the Department of Electrical and Computer Engineering, North Carolina A&T State University. He is an accomplished Researcher. He has received significant funding for his research projects from esteemed national agencies and organizations, including the National Science Foundation (NSF), the Department of Transportation (DOT), the Air Force Research Laboratory (AFRL), NASA, Intel, Cisco, and Lockheed Martin. He has authored or co-authored several publications in prestigious venues. His research has been published in renowned journals, such as IEEE Internet of Things, IEEE Transactions of Dependable and Secure Computing, IEEE Transactions on Human-Machine Systems, and IEEE Transactions of Mobile Computing. He has also contributed to leading conferences, including the International Conference on Communication, International Conference on Pattern Recognition, and International Conference on Wireless Communication. With diverse research interests, his areas of expertise include security and privacy in unmanned aerial systems, smart grids, machine learning applications, vehicular ad hoc networks, and blockchain applications.View more
Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL, USA
Fei Hu (Member, IEEE) received the first Ph.D. degree in signal processing from Tongji University, Shanghai, China, in 1999, and the second Ph.D. degree in electrical and computer engineering from Clarkson University, New York, NY, USA, in 2002. He is currently a Professor with the Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL, USA. His research has been supported by U.S. NSF, DoE, DoD, Cisco, and Sprint. He has published over 200 journal/conference papers and book (chapters) in the field of wireless networks and machine learning. His research interests include wireless networks, machine learning, big data, and network security and their applications.
Fei Hu (Member, IEEE) received the first Ph.D. degree in signal processing from Tongji University, Shanghai, China, in 1999, and the second Ph.D. degree in electrical and computer engineering from Clarkson University, New York, NY, USA, in 2002. He is currently a Professor with the Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL, USA. His research has been supported by U.S. NSF, DoE, DoD, Cisco, and Sprint. He has published over 200 journal/conference papers and book (chapters) in the field of wireless networks and machine learning. His research interests include wireless networks, machine learning, big data, and network security and their applications.View more
Department of Computer Science, The University of Alabama, Tuscaloosa, AL, USA
Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Banha, Egypt
Ahmad Alsharif (Senior Member, IEEE) received the B.Sc. and M.Sc. degrees (Hons.) in electrical engineering from Benha University, Cairo, Egypt, in 2009 and 2015, respectively, and the Ph.D. degree in electrical and computer engineering from Tennessee Tech University, Cookeville, TN, USA, in May 2019. Currently, he is an Assistant Professor with The University of Alabama, Tuscaloosa, AL, USA. He also holds the position of an Assistant Professor with the Faculty of Engineering at Shoubra, Benha University, Egypt. His research interests include applied cryptography, secure protocol design, IoT security, cyber-physical systems security, and the use of machine learning in cybersecurity. In 2022, he received the U.S. National Science Foundation Research Initiation Initiative Grant (NSF CRII); and the Young Innovator Award from the Egyptian Industrial Modernisation Center, in 2009.
Ahmad Alsharif (Senior Member, IEEE) received the B.Sc. and M.Sc. degrees (Hons.) in electrical engineering from Benha University, Cairo, Egypt, in 2009 and 2015, respectively, and the Ph.D. degree in electrical and computer engineering from Tennessee Tech University, Cookeville, TN, USA, in May 2019. Currently, he is an Assistant Professor with The University of Alabama, Tuscaloosa, AL, USA. He also holds the position of an Assistant Professor with the Faculty of Engineering at Shoubra, Benha University, Egypt. His research interests include applied cryptography, secure protocol design, IoT security, cyber-physical systems security, and the use of machine learning in cybersecurity. In 2022, he received the U.S. National Science Foundation Research Initiation Initiative Grant (NSF CRII); and the Young Innovator Award from the Egyptian Industrial Modernisation Center, in 2009.View more