Over the past few years, there have been increased amounts of cyber-physical-attacks on critical infrastructure industries such as Energy, Oil & Gas, Transportation and Pharmaceutical Discovery and Manufacturing. The traditional approach is to reduce the attack surface with firewalls and rule-based Intrusion Detection Systems to detect and keep hackers outside the company network and the ICS. Furthermore, the traditional approaches mainly focus on network activities and user activities but do not consider the sensor and actuator data. During the past few years, Siemens has been exploring new solutions for industrial control security by combining analytical approaches and domain knowledge of process semantics. In this talk, Jiaxing will give an overview on the research progress of applying machine learning solutions for security applications in industrial control system.
Jiaxing Pi is a research scientist with specialization in big data and security analytics in Siemens Corporation, Corporate Technology. Jiaxing obtained his Ph.D. in Industrial and Systems Engineering from University of Florida. After he joined Siemens, he has been working on the research topic of security analytics for various industrial control system. His past projects include intrusion/anomaly detection systems for water treatment plant, power transmission and distribution system and manufacturing plants. He is currently developing the security situation awareness and root cause analysis system for large distributed control system.