Sensor-based cyberattack detection in critical infrastructures using deep learning algorithms

The technology that has evolved with innovations in the digital world has also caused an increase in many security problems. Day by day, the methods and forms of cyberattacks are becoming more complicated; therefore, their detec- tion has become more difficult. In this work, we have used datasets that have been prepared in collaboration with the Raymond Borges and Oak Ridge National Laboratories. These datasets include measurements of the Industrial Control Systems related to chewing attack behavior. These measurements in- clude synchronized measurements and data records from Snort and relays with a simulated control panel. In this study, we developed two models using these datasets. The first is a model we call the DNN model, which was build using the latest deep learning algorithms. The second model was created by adding the AutoEncoder structure to the DNN model. All of the variables used when developing our models were set parametrically. A number of variables such as the activation method, the number of hidden layers in the model, the number of nodes in the layers, and the number of iterations were analyzed to create the optimum model design. When we run our model with optimum settings, we obtained better results than those found in related studies. The learning speed of the model has a 100% accuracy rate, which is also entirely satisfactory. While the training period of the dataset containing about 4 thousand differ- ent operations lasts for about 90 seconds, the developed model completes the learning process at a level of milliseconds to detect new attacks. This increases the applicability of the model in the real-world environment.