Visible to the public Biblio

Filters: Author is McNair, Janise  [Clear All Filters]
2020-10-14
Trevizan, Rodrigo D., Ruben, Cody, Nagaraj, Keerthiraj, Ibukun, Layiwola L., Starke, Allen C., Bretas, Arturo S., McNair, Janise, Zare, Alina.  2019.  Data-driven Physics-based Solution for False Data Injection Diagnosis in Smart Grids. 2019 IEEE Power Energy Society General Meeting (PESGM). :1—5.
This paper presents a data-driven and physics-based method for detection of false data injection (FDI) in Smart Grids (SG). As the power grid transitions to the use of SG technology, it becomes more vulnerable to cyber-attacks like FDI. Current strategies for the detection of bad data in the grid rely on the physics based State Estimation (SE) process and statistical tests. This strategy is naturally vulnerable to undetected bad data as well as false positive scenarios, which means it can be exploited by an intelligent FDI attack. In order to enhance the robustness of bad data detection, the paper proposes the use of data-driven Machine Intelligence (MI) working together with current bad data detection via a combined Chi-squared test. Since MI learns over time and uses past data, it provides a different perspective on the data than the SE, which analyzes only the current data and relies on the physics based model of the system. This combined bad data detection strategy is tested on the IEEE 118 bus system.
2020-08-24
Starke, Allen, Nie, Zixiang, Hodges, Morgan, Baker, Corey, McNair, Janise.  2019.  Denial of Service Detection Mitigation Scheme using Responsive Autonomic Virtual Networks (RAvN). MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM). :1–6.
In this paper we propose a responsive autonomic and data-driven adaptive virtual networking framework (RAvN) that integrates the adaptive reconfigurable features of a popular SDN platform called open networking operating system (ONOS), the network performance statistics provided by traffic monitoring tools such as T-shark or sflow-RT and analytics and decision making skills provided from new and current machine learning techniques to detect and mitigate anomalous behavior. For this paper we focus on the development of novel detection schemes using a developed Centroid-based clustering technique and the Intragroup variance of data features within network traffic (C. Intra), with a multivariate gaussian distribution model fitted to the constant changes in the IP addresses of the network to accurately assist in the detection of low rate and high rate denial of service (DoS) attacks. We briefly discuss our ideas on the development of the decision-making and execution component using the concept of generating adaptive policy updates (i.e. anomalous mitigation solutions) on-the-fly to the ONOS SDN controller for updating network configurations and flows. In addition we provide the analysis on anomaly detection schemes used for detecting low rate and high rate DoS attacks versus a commonly used unsupervised machine learning technique Kmeans. The proposed schemes outperformed Kmeans significantly. The multivariate clustering method and the intragroup variance recorded 80.54% and 96.13% accuracy respectively while Kmeans recorded 72.38% accuracy.