Yan Wang

Computing Power Networks (CPNs) integrate heterogeneous resources across the cloud–edge–end continuum to support wide-area distributed computational services, but the geographical separation of computation and data makes cross-domain data access a major bottleneck. Intelligent cross-domain data orchestration in CPNs is difficult because replica selection and end-to-end path planning must be jointly optimized under Service Level Agreement (SLA) and resource constraints, while each domain observes only partial congestion and resource information. This paper presents AE-MAAC, an attention-enhanced multi-agent reinforcement learning framework that formulates cross-domain data orchestration as a Multi-Agent Markov Decision Process (MMDP) with a hierarchical composite action space and constraint-aware masking under a centralized-training–decentralized-execution paradigm. An attention-based state representation captures heterogeneous cross-domain topology and resource information, an attention-enhanced centralized critic strengthens inter-domain credit assignment in large-scale settings, and parallel dual-policy actors together with a parallel experience ensemble and prioritized sampling improve training stability in large constrained action spaces. Extensive simulations across three CPN scales show that AE-MAAC achieves the highest average episode reward. In the representative 5×10 network, it reaches an average episode reward of 431.7 with a 94.2% request success rate and a 259.8 ms average end-to-end delay, while yielding a lower multi-objective cost than state-of-the-art RL baselines.

Deep learning has proven to be effective for enhancing the accuracy and efficiency of attack detection through training with large sample sizes. However, when applied to cyber–physical systems (CPSs), it still encounters challenges such as scarcity of attack samples, the difficulty of selecting features for high-dimensional data, and weak model-generalization ability. In response, this paper proposes ResADM, a transfer-learning-based attack detection method for CPSs. Firstly, an intentional sampling method was employed to construct different sets of samples for each class, effectively balancing the distribution of CPS-attack samples. Secondly, a feature-selection method based on importance was designed to extract the meaningful features from attack behaviors. Finally, a transfer-learning network structure based on ResNet was constructed, and the training parameters of the source model were optimized to form the network-attack detection method. The experimental results demonstrated that ResADM effectively balanced the data classes and extracted 32-dimensional attack-behavior features. After pre-training on the UNSW-NB15 dataset, ResADM achieved a detection accuracy of up to 99.95% for attack behavior on the CICIDS2017 dataset, showcasing its strong practicality and feasibility.

Element extraction of Network Security Situation is the foundation for Network Security Situation awareness. Traditional methods for network security element extraction struggle with efficiently processing large-scale data and establishing effective cross-level element associations, leading to a higher false alarm rate in situation awareness. This paper proposes a cross-level network security element fusion extraction method based on deep learning. Firstly, through a data preprocessing method based on element correlation, we reduce data dimensionality, addressing the challenge of large-scale nonlinear data processing. Secondly, we employ principal component analysis to construct a method for cross-level network security element fusion extraction. Moreover, by integrating convolutional neural networks and long short-term memory networks, we establish a cross-level network security element fusion classification model, achieving precise perception of the Network Security Situation. Experimental results indicate that the proposed cross-level network security element fusion extraction method effectively reduces dataset dimensions, extracts 32-dimensional crucial network security fusion elements, and achieves a detection accuracy rate of up to 99.99% for network attack behaviors, significantly enhancing the capability of network security situation awareness.

Network attack identification effectively secures Internet of Things (IoT) application scenarios. However, dynamic scene changes, attack feature reliance, high data dimensions, and challenges with spatio-temporal feature fusion frequently pose limitations to attack traffic identification in IoT contexts. Definitive intelligent IoT attack identification enables intelligent algorithms to extract attack features for application scenarios with fixed topological environments but cannot construct the intricate changes of IoT application scenarios. Through the dynamic acquisition, feature awareness, and deep learning, intelligent digital twin-based attack detection can address these issues and enhance attack identification for IoT threats. Thus, this paper proposed an intelligent digital twin method based on spatio-temporal feature fusion for IoT attack behavior identification. Firstly, feature subsets are selected based on information gain to reduce the dimensionality of IoT data with high traffic; Secondly, a parallel spatio-temporal feature extraction model is designed unlike the existing tandem model, which uses a simplified Convolutional Neural Networks (CNN) model to learn the spatial features of the attack, a Bi-directional Long Short-Term Memory (BiLSTM) model to learn the temporal features of the attack, an attention mechanism to fuse the temporal and spatial features, and the (Deep Neural Networks) DNN to learn the combined features; Finally, the virtual instance space and topology of the attack scenario are simulated using digital twin (DT) to build a digital version of the complex system for IoT applications and tested in a simulation environment. Based on experimental results using the UNSW-NB15 and CICIDS2017 datasets, this paper shows that the proposed method can extract spatio-temporal features from network attack traffic and has a 5% improvement in test accuracy.