Sensor attacks compromise the reliability of cyber-physical systems (CPSs) by altering sensor outputs with the objective of leading the system to unsafe system states. This paper studies a probabilistic intrusion detection framework based on $$\lambda $$ -sensor-attack detectability ( $$\lambda $$ -sa), a formal measure that evaluates the likelihood of a system being under attack based on observed behaviors. Our framework enhances detection capabilities by using probabilistic information to detect attacks across the class of all complete, consistent, and successful sensor attack strategies, which enables the detection of sensor attacks that remain undetectable to current detection methodologies. We develop a polynomial-time algorithm that verifies $$\lambda $$ -sa detectability by constructing a weighted verifier automaton and solving the shortest path problem. Additionally, we propose a method to determine the maximum detection confidence level ( $$\lambda $$ *) achievable by the system, ensuring the highest probability of identifying attack-induced behaviors.

Sensor attacks compromise the reliability of cyber-physical systems (CPSs) by altering sensor outputs with the objective of leading the system to unsafe system states. This paper studies a probabilistic intrusion detection framework based on $λ$-sensor-attack detectability ($λ$-sa), a formal measure that evaluates the likelihood of a system being under attack based on observed behaviors. Our framework enhances detection by extending its capabilities to identify multiple sensor attack strategies using probabilistic information, which enables the detection of sensor attacks that were undetected by current detection methodologies. We develop a polynomial-time algorithm that verifies $λ$-sa detectability by constructing a weighted verifier automaton and solving the shortest path problem. Additionally, we propose a method to determine the maximum detection confidence level ($λ$*) achievable by the system, ensuring the highest probability of identifying attack-induced behaviors.

Resilience against cyberattacks is an important requirement of modern cyber-physical systems (CPS) considering the industry 4.0 evolution. In this work, we use the formalism of Discrete Event Systems (DES) to design an approach that aims to protect cyber-physical systems against actuator attacks using event-based symmetric cryptography. In this approach, controllable events that are properly selected are encrypted before being transmitted from the controller to the plant, leading intruders to mistakenly infer the supervisor’s control actions. Thus, it is presumed that attacks on actuators do not have the expected impact on the plant, preventing unsafe states from being reached. The proposed approach is applied to a case study from the literature, where the identification of the attack is done without causing any damage while maintaining the integrity of the system.

The emergence of the Internet of Things (IoT) has led to the deployment of various types of sensors in many application fields, including environment monitoring, smart cities, health, industries, and others. The increasing number of connected devices has led to the creation of massive quantities of data that need to be analyzed. Typically, this data is ordered by time, as a time series. In this context, this paper presents a time series prediction model based on Recurrent Neural Networks in order to predict one step ahead. Result obtained through five Internet of Things monitoring datasets, showed that the Recurrent Neural Network obtained better performance that the prediction methods, ARIMA and SVM.