| Title | Network Intrusion Detection in Smart Grids for Imbalanced Attack Types Using Machine Learning Models |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Roy, D. D., Shin, D. |
| Conference Name | 2019 International Conference on Information and Communication Technology Convergence (ICTC) |
| Date Published | oct |
| Keywords | advanced metering infrastructure, automatic meter reading, boosting, Collaboration, composability, critical security service, generation power grid paradigm, Human Behavior, imbalanced attack types, imbalanced data, Intrusion detection, learning (artificial intelligence), legacy information, low detection rates, machine learning, machine learning algorithms, machine learning models, Metrics, network intrusion detection, ongoing attacks, policy-based governance, power engineering computing, privacy, privacy concerns, pubcrawl, resilience, Resiliency, Scalability, security, security of data, Smart grid, smart grid consumer privacy, smart grid systems, Smart grids, smart information, smart meter, smart power grids, system operator, time information, time-of-use pricing, Training |
| Abstract | Smart grid has evolved as the next generation power grid paradigm which enables the transfer of real time information between the utility company and the consumer via smart meter and advanced metering infrastructure (AMI). These information facilitate many services for both, such as automatic meter reading, demand side management, and time-of-use (TOU) pricing. However, there have been growing security and privacy concerns over smart grid systems, which are built with both smart and legacy information and operational technologies. Intrusion detection is a critical security service for smart grid systems, alerting the system operator for the presence of ongoing attacks. Hence, there has been lots of research conducted on intrusion detection in the past, especially anomaly-based intrusion detection. Problems emerge when common approaches of pattern recognition are used for imbalanced data which represent much more data instances belonging to normal behaviors than to attack ones, and these approaches cause low detection rates for minority classes. In this paper, we study various machine learning models to overcome this drawback by using CIC-IDS2018 dataset [1]. |
| DOI | 10.1109/ICTC46691.2019.8939744 |
| Citation Key | roy_network_2019 |
Network Intrusion Detection in Smart Grids for Imbalanced Attack Types Using Machine Learning Models