Unmanned Aerial Vehicle (UAV) swarm networks have been presented as a promising paradigm for conducting monitoring, and inter-connecting tasks in unattended or even hostile environments. However, harsh deployment scenario may make the UAVs susceptible to large-scale damage, and thus degrades the connectivity and performance of the network. None of existing technologies can effectively re-organize the surviving UAVs in a severely damaged UAV swarm into a unified UAV Swarm Network (USNET), this paper presents and analyzes the damage-resilience problem of USNETs for the first time, and put forwards a Swarm Intelligence-based Damage-Resilient (SIDR) mechanism. First, a damage model of USNETs and several metrics are defined before the problem is formally formulated. Second, the SIDR mechanism is detailed based on comprehensively utilizing the storage, communication, positioning, and maneuvering capabilities of UAVs. Third, a potential-field-based solution to the proposed SIDR mechanism is presented, aiming to recover a USNET rapidly and elastically. At last, an evaluation environment is built on the OMNeT++ platform, and the proposed SIDR mechanism is implemented. Extensive simulations are conducted in both dynamic and static scenarios. Simulation results demonstrate that SIDR outperforms the existing algorithms in terms of resilience capability, convergence time and communication overhead. Even if a USNET is divided into multiple disjoint subnets with arbitrary shape, SIDR can aggregate the surviving nodes into a connected network while the network is still flying along the flight path during the recovery process.

Botnets pose a significant challenge in network security by leveraging Domain Generation Algorithms (DGA) to evade traditional security measures. Extracting DGA domain samples is inherently complex, and the current DGA detection models often struggle to capture domain features effectively when facing limited training data. This limitation results in suboptimal detection performance and an imbalance between model accuracy and complexity. To address these challenges, this paper introduces a novel multi-scale feature fusion model that integrates the Transformer architecture with the Rapid Selective Kernel Network (R-SKNet). The proposed model employs the Transformer’s encoder to couple the single-domain character elements with the multiple types of relationships within the global domain block. This paper proposes integrating R-SKNet into DGA detection and developing an efficient channel attention (ECA) module. By enhancing the branch information guidance in the SKNet architecture, the approach achieves adaptive receptive field selection, multi-scale feature capture, and lightweight yet efficient multi-scale convolution. Moreover, the improved Feature Pyramid Network (FPN) architecture, termed EFAM, is utilized to adjust channel weights for outputs at different stages of the backbone network, leading to achieving multi-scale feature fusion. Experimental results demonstrate that, in tasks with limited training samples, the proposed method achieves lower computational complexity and higher detection accuracy compared to mainstream detection models.

Traditional Internet protocol networks cannot provide the service of selecting a secure path to transmit various types of data with specific security constraints. First, to solve the “secure path transmission” problem, this paper first proposes a search-transmit model for secure network path transmission, i.e., to find a multi-attribute optimized path that meets the specific security requirements in the search phase, and then transmit the packets along the optimized path in the transmission phase. Second, we propose a solution to the search-transmit model. The idea of the solution is to use the particle swarm optimization algorithm to search for a secure path that meets the multi-attribute requirements and then set the source route on the router to control the packet transmission. Finally, a prototype system based on network function virtualization is developed to evaluate the feasibility and performance of the proposed solution. Experimental results show that the proposed solution outperforms existing algorithms in terms of performance.

Harsh or hostile environments may lead to node failure and connectivity degradation of a UAV swarm system. In order to maintain or restore the connectivity of a network in case of node failure, this paper proposes a mechanism to adjust the network topology to resist the impact caused by node failure. Firstly, a network model of a UAV swarm network based on k-hop constrained reachability is proposed. Secondly, a k-hop constrained reachability based proactive connectivity maintaining mechanism of UAV swarm network is presented. In this mechanism, each node identifies the network abnormality distributed according to k-hop reachability, and reports the observed abnormality to the master node; then, a virtual edge-based topology reconstruction algorithm is put forward for the master node to derive a topology reconstruction solution in a centralized way; afterwards, the solution is delivered to the slave nodes to reconfigure the network topology in parallel. Thirdly, a quantitative method is introduced to optimize the total travel distance of nodes, and a spanning tree-based method is designed to maintain the connectivity during the topology transformation process. Both theoretical analysis and simulation results have shown that: on the one hand, the proposed mechanism are effective in maintaining a UAV swarm’s connectivity in case of node failure; on the other hand, the proposed mechanism outperforms existing mechanisms in terms of fault tolerance, connectivity, and total travel distance, and it’s less affected by the failure rate.

Alzheimer's disease is a severe neurodegenerative disorder that primarily affects the elderly. Early detection is crucial for enabling timely interventions and slowing the disease's progression. A promising approach for early detection involves analyzing audio data collected from elderly individuals in their homes using Internet of Things (IoT) devices. However, this method presents significant challenges concerning privacy and data security. This paper introduces EDP-AD (Efficient Differential Privacy-Alzheimer's Detection), an efficient and privacy-preserving system. The system utilizes small IoT devices to collect audio data from elderly individuals. By integrating machine learning, federated learning (FL) and differential privacy (DP) techniques, EDP-AD ensures that raw audio data remains local while breaking down data silos, thereby preventing potential privacy leaks during the disease detection process. To enhance system efficiency, a sparse mask updating algorithm based on Top-k is proposed. This algorithm reduces communication overhead by sparsifying the model parameters uploaded by clients within the FL framework. Evaluation on a real-world dataset shows that the system achieves an accuracy rate of 84.48%, reduces communication costs by two-thirds, and provides robust privacy protection while maintaining high efficiency.