Wireless body area networks (WBANs) have to address jamming attacks to support health-care applications. In this paper, we present a reinforcement learning based power control scheme for the communication between the in-body sensors and the WBAN coordinator to resist jamming attacks. This scheme applies Q-learning to guide the coordinator to achieve an optimal power control strategy without being aware of the in-body sensor’s transmission parameters and the WBAN model of the other sensors in the dynamic anti-jamming transmission. Additionally, a transfer learning method is adopted to accelerate the learning speed. Stackelberg equilibria and their existence conditions are deduced in a single time slot to upper bound the performance of the learning based sensor power control scheme. Simulation results show that the proposed scheme can efficiently increase the utilities and decrease the transmission energy consumptions for the in-body sensors and the WBAN coordinator, and simultaneously reduce the attack possibility of the jammer compared with standard Q-learning based sensor power control scheme.
For modern information systems, robust access control mechanisms are vital in safeguarding data integrity and ensuring the entire system’s security. This paper proposes a novel semi-supervised learning framework that leverages heterogeneous graph neural network-based embedding to encapsulate both the intricate relationships within the organizational structure and interactions between users and resources. Unlike existing methods focusing solely on individual user and resource attributes, our approach embeds organizational and operational interrelationships into the hidden layer node embeddings. These embeddings are learned from a self-supervised link prediction task based on a constructed access control heterogeneous graph via a heterogeneous graph neural network. Subsequently, the learned node embeddings, along with the original node features, serve as inputs for a supervised access control decision-making task, facilitating the construction of a machine-learning access control model. Experimental results on the open-sourced Amazon access control dataset demonstrate that our proposed framework outperforms models using original or manually extracted graph-based features from previous works. The prepossessed data and codes are available on GitHub,facilitating reproducibility and further research endeavors.
Wireless body area networks (WBANs) are essential for real-time health monitoring using physiological sensors, but these sensors have limitations in computing power, storage, and battery life. To address these issues, we propose a cloud-edge computing architecture where data from sensors are initially processed by WBAN edge devices (smartphones, PDAs) before being offloaded to cloud servers for extensive analysis. We model the offloading decision as a Markov decision process (MDP) and design a system utility function that balances processing latency, power consumption, and the quality of communication. Traditional deep reinforcement learning algorithms like deep deterministic policy gradient (DDPG) optimize MDPs but face slow convergence and local optima issues. To overcome these, we introduce a multi-step deep deterministic policy gradient (MSDDPG) algorithm that uses a multi-step update mechanism, enhancing learning efficiency and solution accuracy. Experimental results show that MSDDPG significantly reduces processing delay and energy consumption while improving system utility. Additionally, our approach considers WBAN edge device constraints, ensuring practical applicability, extending device battery life, and enhancing performance in real-world scenarios.