Search for: All records

Industrial Control Systems (ICS) are used to control physical processes in critical infrastructure. These systems are used in a wide variety of operations such as water treatment, power generation and distribution, and manufacturing. While the safety and security of these systems are of serious concern, recent reports have shown an increase in targeted attacks aimed at manipulating physical processes to cause catastrophic consequences. This trend emphasizes the need for algorithms and tools that provide resilient and smart attack detection mechanisms to protect ICS. In this paper, we propose an anomaly detection framework for ICS based on a deep neural network. The proposed methodology uses dilated convolution and long short-term memory (LSTM) layers to learn temporal as well as long term dependencies within sensor and actuator data in an ICS. The sensor/actuator data are passed through a unique feature engineering pipeline where wavelet transformation is applied to the sensor signals to extract features that are fed into the model. Additionally, this paper explores four variations of supervised deep learning models, as well as an unsupervised support vector machine (SVM) model for this problem. The proposed framework is validated on Secure Water Treatment testbed results. This framework detects more attacks in a shorter period of time than previously published methods. 

Industrial Control Systems (ICS) are the brain and backbone of nation's critical infrastructure such as nuclear power, water treatment, and petrochemical plants. In order to increase interoperability, real-time availability of data, and flexibility, information/communication technologies are adopted in this domain. While these information technologies have been effective, they are integrated into operational technologies without the necessary security defense. Designing an effective, layered security defense is not possible unless security threats are identified through a structural analysis of the ICS. For that reason, this paper provides an attacker's point of view on the reconnaissance effort necessary to gather details of the system dynamics - which are required for the development of sophisticated attacks. We present a reconnaissance approach which uses the system's I/O data to infer the dynamic model of the system. In this effort, we propose a novel cyber-attack which targets the controller proportional-integral-derivative gain values in a constant setpoint control system. Our findings will help researchers design more secure control systems.