To enhance dependable resource allocation against increasing DDoS attacks, in this paper, we investigate interactions between a sensor device-edgeVM pair and a DDoS attacker using a game-theoretic framework, under the constraints of the task time, resource budget, and incomplete knowledge of the processing time of machine learning tasks. In this game, the sensor device expects an edgeVM to cooperate and choose its resource allocation strategy with the objective of satisfying the minimum resource required of machine learning tasks at the corresponding sensor device. Similarly, the attacker’s objective is to strategically allocate resources so that the resource constraint of the machine learning tasks is not satisfied. Owing to a lack of complete information of the processing time of the machine learning tasks, this strategic resource allocation problem between the two players is modeled as a Bayesian Q-learning game, in which the optimal strategies of the sensor device-edgeVM pair and the attacker are analyzed. Furthermore, probability distributions are employed by the corresponding players to model the incomplete nature of the game and a greedy Q-learning algorithm is proposed to dependable resource allocation against DDoS attacks. Numerical simulation results demonstrate that the proposed mechanism is superior to other dependable resource allocation mechanisms under incomplete information for DDoS attacks in the sensor edge cloud.

To ensure an accurate power allocation against increasing intelligent jamming attacks on the offloading link of computation tasks, we investigate interactions between a cluster head node and an intelligent jammer using a Stackelberg game framework, under the constraint of the total power to use and the limited knowledge of its own channel gain for each player. In this game, the intelligent jammer gathers channel gain information and processes it using a deep neural network (DNN) to infer the accurate jamming power as an attack strategy. The cluster head node also exploits DNN to infer an accurate transmission power as a defense strategy according to the varying channel gain. We model the optimization of the attack and defense strategies using single channel jamming DNN (SJnet), multiple channel jamming DNN (MJnet), single channel sensor DNN (SSnet), and multiple channel sensor DNN (MSnet) for the single (multiple) channel jamming attacks. In addition, we extend the design to the scenario where the intelligent jammer can launch a hybrid mode jamming attack, and propose a DNN Stackelberg game-based defense scheme. Numerical simulation results demonstrate that our proposed mechanism is superior to other power allocation mechanisms under different scenarios in the sensor edge cloud.

Sensor-cloud computing is envisioned as a promising technology that can integrate various services by extending the computational capabilities of physical sensor nodes. It is prone to attack because of special characteristics of physical sensor nodes and virtual sensor-service nodes. Considering the intrusion detection threshold, false alarm probability of the intrusion detection system (IDS), and three different attacked scenarios, we devise a physical IDS (PIDS)-to-gateway and virtual IDS (VIDS)-to-gateway detection model for Sensor-Cloud. We formulate a two-layer gateway-assisted detection and defense decision problem involving multiple IDSs using an evolutionary game in order to optimize the intrusion detection strategy for lowering energy consumption and reducing alarm messages. We derive an evolutionary stable strategy and prove that the proposed mechanism achieves Nash equilibrium, such that each IDS completes cooperatively defense tasks. We propose a game-theoretic approach to achieve an energy-efficient cooperative defense scheme for sensor-cloud computing environments. The simulation results demonstrate that the proposed mechanism achieves energy-efficient defense and increases security of data in the Sensor-Cloud.

Heterogeneous wireless sensor networks (WSNs) are widely deployed, owing to their good capabilities in terms of network stability, dependability, and survivability. However, they are prone to the spread of malware because of the limited computational capabilities of sensor nodes. To suppress the spread of malware, a malware spread model is urgently required to discover the rules of malware spread. In this paper, a heterogeneous susceptible-iNsidious-infectious-recovered-dysfunctional (SNIRD) model was proposed, which not only considers the communication connectivity of heterogeneous sensor nodes but also reflects the characteristics of malware hiding and dysfunctional sensor nodes. Then, the fraction evolution equations of heterogeneous sensor nodes in different states in discrete time were obtained. Furthermore, the existence of equilibria for the heterogeneous SNIRD model was proved, and the malware spread threshold was obtained, which indicates whether malware will spread or fade out. Finally, the heterogeneous SNIRD model was simulated and it was contrasted with the conventional SIS and SIR models to validate its effectiveness. The results construct a theoretical guideline for administrators to suppress the spread of malware in heterogeneous WSNs.