Cybersecurity Center

VCU Cybersecurity Center Focus Area: Resilience and Cybersecurity

VCU Resilience and Cybersecurity focus area is lead by Prof. Milos Manic.

Dr. Manic is a Professor with Computer Science Department and Director of Modern Heuristics Research Group at Virginia Commonwealth University. He has over 20 years of academic and industrial experience. His previous positions include tenured positions with University of Idaho, director of the Computer Science Program at Idaho Falls, University of Nis, Serbia, and a Fellow of the Brain Korea 21 Program. As principal investigator he lead number of research grants with the National Science Foundation, Idaho EPSCoR, Dept. of Energy, Idaho National Laboratory, Dept. of Air Force, Fujitsu Laboratories of America, Hewlett-Packard, in the area of data mining and computational intelligence applications in process control, human-machine interaction, network security, and infrastructure protection.

Dr. Manic is a founding Chair (2011-2015) of IEEE IES Technical Committee on Resilience and Security for Industrial Applications(ReSia); He has organized first National Workshop on Resilience Research for Critical Infrastructures, NSF Award ID: 1551895, https://cps-vo.org/group/NWRR2015. Dr. Manic is co-founder and Gen. Co-Chair (2008-2011) of IEEE IES International Symposium on Resilient Control Systems, ISRCS, which evolved into Resilience Week.
Recepient of 2018 R&D 100 Award for Autonomic Intelligent Cyber Sensor (AICS)

Funded Projects

Integrated Cyber-Physical Assessment and Response

In this project, VCU MHRG research group is involved in DOE’s multi National Lab IJC3 R&D effort. MHRG’s effort is addressing ways of enhancing human response to cyber and physical threats within Cyber-Physical Systems (CPS). This work looks at degradation, data-fusion, and visualization techniques and their applications within CPS architectures. Along with prototype of predictive visualization, the work indicates future methodologies that help characterize and classify the diverse behaviors in CPS.

Supported by: BEA/DOE | Faculty: Dr. Milos Manic

Integrated Cyber-Physical Assessment and Response

Resilient, Scalable Cyber State Awareness of Industrial Control System Networks To Threat: Data Driven Modeling

In this project, VCU MHRG is collaborating with the Idaho National Laboratory and University of Idaho to develop an intelligent agent for increasing the cyber state awareness of an Industrial Control System. The system performs real time inferences on the cyber and physical data of the system and generates warnings to the operators on any sub-optimal behavior and possible malicious attacks. The monitoring and operational health assessment of the ICS is entirely data driven.

Supported by: BEA/DOE | Faculty: Dr. Milos Manic

Resilient, Scalable Cyber State Awareness

Multi-agent Analysis to Characterize Complex Infrastructure Interdependencies

In this project, a Microgrid Simulator software was developed by our group to simulate and understand the dynamics of a microgrid. The simulation provides the user the means to run the micro-grid model, set the load at the available load sectors; set the desired power generation supplied by the available generators; set the voltage regulating transformer impedances. Further it provides the user feedback about status of the micro-grid in terms of the actual generation supplied to the micro-grid and the load voltage demands met based on control settings provided by the user in the control panel. The control panel is designed as such in order to enable future design work of multi-agent controllers to control the power inputs to the micro-grid and manage stability.

Supported by: BEA/DOE | Faculty: Dr. Milos Manic

Multi-agent Analysis to Characterize Complex Infrastructure Interdependencies

'Known Secure' Process Measurements for Attack Detection

This project focuses on developing a Known Secure Sensor Measurements (KSSM) algorithm for detecting unauthorized process manipulation and falsification of the state of a control process. The primary contribution of the proposed KSSM algorithm is increased cyber security and state-awareness of the control system, The algorithm detects process state deception by an intelligent adversary through secure sensor placement and randomized sensor selection.

Supported by: BEA/DOE | Faculty: Dr. Milos Manic

Known Secure Process Measurements for Attack Detection

Experimental Security Vulnerability Estimation

In this project, VCU-MHRG proposed bug classification methodology that uses the short and long descriptions of bug reports in publicly available bug databases, and advanced text mining techniques coupled with machine learning algorithms to aid discovery of hidden impact vulnerabilities. The implementation of the proposed classifier was initiated for the Linux kernel vulnerabilities by using the Redhat Bugzilla bug database as the source of bug descriptions. The classifier was tested on 1000 randomly selected normal bugs out of which 76 were known hidden impact vulnerabilities. On the average, 71% of the hidden impact vulnerabilities were identified correctly.

Supported by: BEA/DOE | Faculty: Dr. Milos Manic

Experimental Security Vulnerability Estimation

Resilient Control System Network Agents

In the first phase, this project aimed at tailoring an intrusion detection system to the specifics of critical infrastructures, which have the potential of significantly improving the security of such systems. The IDS-NNM – Intrusion Detection System using Neural Network based Modeling was developed. In the second phase, this project focused on the development of network security cyber-sensor and its learning algorithm. The learning algorithm constructed a fuzzy logic rule base modeling the normal network behavior. The performance of the system was evaluated on a set of network data recorded from an experimental test-bed mimicking the environment of a critical infrastructure control system.

Supported by: BEA/DOE | Faculty: Dr. Milos Manic

Resilient Control System Network Agents

Intelligent Sensor and Data Fusion

A smart grid is an intelligent power grid that is capable of meeting the demand response in an optimized manner with available resources of power generation. Apart from optimizing the power flow in the grid, this intelligent grid must also be able to withstand strong disturbances such as lightning that could shut down the grid or parts of the grid. This project applies methods of Computational Intelligence towards the ultimate goal of creating a resilient energy delivery systems.

Supported by: Department of Energy | Faculty: Dr. Milos Manic

Intelligent Sensor and Data Fusion

All Hazards Critical Infrastructure Knowledge Framework

In this project, VCU MHRG was developing a knowledge database of critical infrastructure hazards. The goal was to develop knowledge base automatically by extracting information about past critical infrastructure hazards from publicly available news articles. As a first step, a web crawler was designed and implemented to extract the portions of text in news articles which carries the important parts of the story. This was carried out using a combination of text mining, feature extraction and machine learning techniques.

Supported by: Department of Energy | Faculty: Dr. Milos Manic

All Hazards Critical Infrastructure Knowledge Framework

Selected cybersecurity publications

Journals:

  1. R. Fernandez Molanes, K. Amarasinghe, J. Rodriguez-Andina and M. Manic, "Deep Learning and Reconfigurable Platforms in the Internet of Things: Challenges and Opportunities in Algorithms and Hardware," in IEEE Industrial Electronics Magazine, vol. 12, no. 2, pp. 36-49, June 2018.PDF, DOI: doi: 10.1109/MIE.2018.2824843
  2. M. Manic, K. Amarasinghe*, J. J. Rodriguez-Andina, C. Rieger, "Intelligent Buildings of the Future: Cyberaware, Deep Learning Powered, and Human Interacting," in IEEE Industrial Electronics Magazine, Vol. 10, Issue 4, pp.32-49, Dec. 21, 2016. DOI: 10.1109/MIE.2016.2615575 (IF 10.71 from Oct. 2017)
  3. K. Derr, M. Manic, "Wireless Sensor Networks - Node Localization for Various Industry Problems," in IEEE Transactions on Industrial Informatics, Jan. 2015. PDF, DOI: 10.1109/TII.2015.2396007 (IF 6.674 from Feb. 2018)
  4. D. Wijayasekara*, O. Linda*, M. Manic, C. Rieger, "FN-DFE: Fuzzy-Neural Data Fusion Engine for Enhanced Resilient State-Awareness of Hybrid Energy Systems," in IEEE Transactions on Cybernetics, vol. 44, no. 11, pp. 2168-2267, Nov. 2014. DOI: 10.1109/TCYB.2014.2323891 (replaced the IEEE Trans on SMC Part B: Cybernetics on January 1, 2013; Part B 2013/14 IF=3.781).
  5. D. Wijayasekara*, O. Linda*, M. Manic, C. Rieger, "Mining Building Energy Management System Data Using Fuzzy Anomaly Detection and Linguistic Descriptions," Industrial Informatics, IEEE Transactions, Publication Year: 2014 , Volume: 10, Issue: 3, Page(s): 1829 – 1840. DOI: 10.1109/TII.2014.2328291. (IF 8.785 from 2014)
  6. Vollmer, T.*, Manic, M., Cyber-Physical System Security with Deceptive Virtual Hosts for Industrial Control Networks, Industrial Informatics, IEEE Transactions, Publication Year: 2014 , Volume: 10, Issue: 2, Page(s): 1337- 1347. DOI: 10.1109/TII.2014.2304633. (IF 8.785)
  7. Vollmer, T.*, Manic, M., Autonomic Intelligent Cyber Sensor to Support Industrial Control Network Awareness", Industrial Informatics, IEEE Transactions, Publication Year: 2014 , Volume: 10 , No. 2, May 2014, Page(s): 1647 - 1658. DOI: 10.1109/TII.2013.2270373. (IF 8.785)
  8. Derr, K.*, and Manic, M., “Adaptive Control Parameters for Dispersal of Multi-Agent Mobile Ad Hoc Network (MANET) Swarms,” Industrial Informatics, IEEE Transactions on, Volume: 9 , Issue: 4, Publication Year: 2013, Page(s): 1900-1911. DOI: 10.1109/TII.2012.2228870. (IF 8.785)
  9. Derr, K.*, and Manic, M., “"Wireless Sensor Network Configuration, Part I: Mesh Simplification for Centralized Algorithms,” Industrial Informatics, IEEE Transactions on, Publication Year: 2013 , Volume: 9 , Issue: 3, Page(s): 1717-1727. DOI: 10.1109/TII.2013.2245906. (IF 8.785)
  10. Derr, K.*, and Manic, M., “Wireless Sensor Network Configuration, Part II: Adaptive Coverage for Decentralized Algorithms,” Industrial Informatics, IEEE Transactions on, Volume: 9 , Issue: 3, Publication Year: 2013 , Page(s): 1728-1738. . DOI: 10.1109/TII.2013.2245907. (IF 8.785)
  11. Linda, O.*, M. Manic, " General Type-2 Fuzzy C-Means Algorithm for Uncertain Fuzzy Clustering," Fuzzy Systems, IEEE Transactions on, vol.20, no.5, pp.883 – 897, Oct. 2012. DOI: 10.1109/TFUZZ.2012.2187453. (IF 6.306) from Sep. 2014)
  12. K. Derr, M. Manic, "Extended Virtual Spring Mesh (EVSM): The Distributed Self Organizing Mobile Ad Hoc Network for Area Exploration," in IEEE Trans. on Industrial Electronics, vol. 58, no. 12, pp. 5424-5437, Dec. 2011. DOI: 10.1109/TIE.2011.2130492. (IF 6.5)
  13. Wijayasekara, D. S.*, Manic, M., Sabharwall, P., and Utgikar, V., “Optimal Artiļ¬cial Neural Network Architecture Selection for Performance Prediction of Compact Heat Exchanger with the EBaLM-OTR Technique,” Nuclear Engineering Design, Vol. 241.7, pages 2549 – 2557, July 2011. (IF 0.972) (DOI: 10.1016/j.nucengdes.2011.04.045)
  14. Linda, O.*, and Manic, M., “Interval Type-2 Fuzzy Voter Design for Fault Tolerant Systems,” Information Science, Vol. 181.14, pages 2933 – 2950, July 2011. (IF 3.893) (DOI: 10.1016/j.ins.2011.03.008)
  15. Linda, O.*, and Manic, M., “Online Spatio-Temporal Risk Assessment for Intelligent Transportation Systems,” Intelligent Transportation Systems, IEEE Transactions on, vol.12, no.1, pp.194- 200, March 2011. DOI: 10.1109/TITS.2010.2076807 (IF 2.472)
  16. Ridluan, A.*, Manic, M., and Tokuhiro, A., “EBaLM-THP- Artificial Neural Network Thermo-Hydraulic Prediction Tool for an Advanced Nuclear Components,” Nuclear Engineering and Design, Vol. 239.2, pages 308 – 319, Feb. 2009. (10.1016/j.nucengdes.2008.10.027) (IF 0.972)

Conferences:

  1. K. Amarasinghe, M. Manic, "Improving User Trust on Deep Neural Networks based Intrusion Detection Systems" in Proc. 44rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2018, Washington DC, USA, Oct. 21-23, 2018.
  2. C. Wikramasinghe, D. Marino, K. Amarasinghe, M. Manic, "Generalization of Deep Learning For Cyber-Physical System Security: A Survey" in Proc. 44rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2018, Washington DC, USA, Oct. 21-23, 2018.
  3. D. Marino, C. Wikramasinghe, M. Manic, "An Adversarial Approach for Explainable AI in Intrusion Detection Systems" in Proc. 44rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2018, Washington DC, USA, Oct. 21-23, 2018.
  4. D. Marino, C. Wikramasinghe, M. Manic, "An Adversarial Approach for Explainable AI in Intrusion Detection Systems" in Proc. 44rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2018, Washington DC, USA, Oct. 21-23, 2018.
  5. K. Amarasinghe, C. Wickramasinghe, D. Marino, C.Rieger, M. Manic, "Framework for Data Driven Health Monitoring of Cyber-Physical Systems" , IEEE Resilience Week (RW) 2018, Denver, CO, USA, Aug, 20-23, 2018.
  6. K. Amarasinghe, C. Wickramasinghe, D. Marino, C.Rieger, M. Manic, "Framework for Data Driven Health Monitoring of Cyber-Physical Systems" , IEEE Resilience Week (RW) 2018, Denver, CO, USA, Aug, 20-23, 2018.
  7. P. Sivils, C. Rieger, K. Amarasinghe, M. Manic, “Integrated Cyber Physical Assessment and Response for Improved Resiliency”, chapter in The Internet of Things for Smart Urban Ecosystems, Ed.s F. Cicirelli, A. Guerrieri, C. Mastroianni, G. Spezzano, A. Vinci, Springer, 2018.
  8. K. Amarasinghe, K. Kenney, and M. Manic, "Toward Explainable Deep Neural Network based Anomaly Detection", in Proc. 11th International Conference on Human System Interaction, IEEE HSI 2018, Gdansk, Poland, July, 04-06, 2018.
  9. D. Marino, M. Anderson, K. Kenney, and M. Manic, “Interpretable data-driven modeling in biomass preprocessing,” in Proc. 11th International Conference on Human System Interaction, IEEE HSI 2018, Gdansk, Poland, July, 04-06, 2018.
  10. C. Wikramasinghe, K. Amarasinghe, D. Marino, and M. Manic, “Deep Self-Organizing Maps for Visual Data Mining,” in Proc. 11th International Conference on Human System Interaction, IEEE HSI 2018, Gdansk, Poland, July, 04-06, 2018.
  11. M. Stuart*, M. Manic, "Survey of Progress in Deep Neural Networks for Resource-Constrained Applications", in Proc. 43rd Annual Conference of the IEEE Industrial Electronics Society, IEEE IECON 2017, Beijing, China, Oct. 29- Nov. 1, 2017.
  12. D. Marino*, K. Amarasinghe*, M. Anderson, N. Yancey, Q. Nguyen, K. Kenney, M. Manic , "Data driven decision support for reliable biomass feedstock preprocessing" , in Proc. 2017 IEEE Symposium on Resilience Week, Wilmington, DE, USA, Sep. 18-22, 2017.
  13. K. Amarasinghe*, D. Marino*, M. Manic, "Deep learning for Energy Load Forecasting" in Press. in Proc. 26th International Symposium on Industrial Electronics, IEEE ISIE 2017, Edinburgh, Scotland, June. 19-21, 2017.
  14. S. R. Pouri, D. Wijayasekara*, M. Manic, S. Phongikaroon, "Development of a Smart Signal Detection Method for Cyclic Voltammetry via Artificial Neural Intelligence," in Press. 2016 American Nuclear Society Winter Meeting and Expo, Las Vegas, NV, Nov. 6-10, 2016. http://www.ans.org/meetings/m_147
  15. K. Amarasinghe*, M. Manic, R. Hruska*, "Optimal Stop Word Selection for Text Mining in Critical Infrastructure Domain," in Proc. IEEE Symposium on Resilience Control Systems, ISRCS 2015, Philadelphia, PA, Aug. 18-20, 2015. DOI: 10.1109/RWEEK.2015.7287440
  16. D. Wijayasekara*, M. Manic, M. McQueen, "Vulnerability Identification and Classification Via Text Mining Bug Databases," in Proc. 40th Annual Conference of the IEEE Industrial Electronics Society, IEEE IECON 2014, Dallas, TX- USA, Oct. 29 - Nov. 1, 2014.
  17. D. Wijayasekara*, M. Manic, "Data Driven Fuzzy Membership Function Generation for Increased Understandability," in Proc. of FUZZ-IEEE, 2014, within, IEEE World Congress On Computational Intelligence, WCCI 2014, Beijing, China, July 6-11, 2014.
  18. O. Linda, D. Wijayasekara*, M. Manic, M. McQueen, "Optimal Placement of Phasor Measurement Units in Power Grids Using Memetic Algorithms," in Proc. IEEE International Symposium on Industrial Electronics, ISIE 2014, Istanbul, Turkey, June 1-4, 2014.
  19. M. Manic, D. Wijayasekara*, K. Amarasinghe*, J. Hewlett, K. Handy, C. Becker, B. Patterson, R. Peterson, "Next Generation Emergency Communication Systems via Software Defined Networks," in Proc. GENI Research and Educational Experiment Workshop (GREE 2014) - Jointly with the 19th GENI Engineering Conference (GEC 19), Atlanta Georgia, Mar. 19-20 2014.
  20. U. Ravishankar*, M. Manic, C. Rieger, "A Micro-Grid Simulator Tool (SGridSim) using Effective Node-to-Node Complex Impedance (EN2NCI) Models," in Proc. IEEE Symposium on Resilience Control Systems, ISRCS 2013, San Francisco, California, Aug. 13-15, 2013.
  21. Linda, O.*, Giani, A., Manic, M., McQueen, M., "Multi-Criteria Based Staging of Optimal PMU Placement using Fuzzy Weighted Average," in Proc. of IEEE International Symposium on Industrial Electronics, Taiwan, Taipei, May 28-31, 2013.

* denotes student co-author