Journal of Network and Computer Applications最新文献

This study introduces a groundbreaking method for predicting network quality in LTE and 5G environments using only GPS data, focusing on pinpointing specific locations within a designated area to determine network quality as either good or poor. By leveraging machine learning algorithms, we have successfully demonstrated that geographical location can be a key indicator of network performance. Our research involved initially classifying network quality using traditional signal strength metrics and then shifting to rely exclusively on GPS coordinates for prediction. Employing a variety of classifiers, including Decision Tree, Random Forest, Gradient Boosting and K-Nearest Neighbors, we uncovered notable correlations between location data and network quality. This methodology provides network operators with a cost-effective and efficient tool for identifying and addressing network quality issues based on geographic insights. Additionally, we explored the potential implications of our study in various use cases, including healthcare, education, and urban industrialization, highlighting its versatility across different sectors. Our findings pave the way for innovative network management strategies, especially critical in the contexts of both LTE and the rapidly evolving landscape of 5G technology.

The proliferation of IoT devices has led to a surge in network traffic, resulting in higher energy usage and response delays. In-network caching has emerged as a viable solution to address this issue. However, caching IoT data faces two key challenges: the transient nature of IoT content and the unknown spatiotemporal content popularity. Additionally, the use of a global view on dynamic IoT networks is problematic due to the high communication overhead involved. To tackle these challenges, this paper presents an adaptive management approach that jointly optimizes caching and communication in IoT networks using a novel bi-level control method called BC3. The approach employs two types of controllers: a global ILP-based optimal controller for long-term timeslots and local learning-based controllers for short-term timeslots. The long-term controller periodically establishes a global cache policy for the network and sends specific cache rules to each edge server. The local controller at each edge server solves the joint problem of bandwidth allocation and cache adaptation using deep reinforcement learning (DRL) technique. The main objective is to minimize energy consumption and system response time with utilizing the global and local observations. Experimental results demonstrate that the proposed approach increases cache hit rate by approximately 12% and uses 11% less energy compared to the other methods. Increasing the cache hit rate can lead to a reduction in about 17% in response time for user requests. Our bi-level control approach offers a promising solution for leveraging the network's global visibility while balancing communication overhead (as energy consumption) against system performance. Additionally, the proposed method has the lowest cache eviction, around 19% lower than the lowest eviction of the other comparison methods. The eviction metric is a metric to evaluate the effectiveness of adaptive caching approach designed for transient data.

Current blockchain systems have high requirements on network connection and data transmission rate, for example, nodes have to receive the latest blocks in time to update the blockchain, nodes have to immediately broadcast the generated block to other nodes for consensus, which restricts the blockchain to run only on real-time connection networks, but the existence of delay tolerant networks poses a great challenge to the deployment of blockchain systems. To address this challenge, a novel blockchain transaction mechanism is proposed. First, the block structure is modified by adding a flag, and on this basis, the definition of the extrachain is proposed. Secondly, based on the blockchain transaction process, transaction verification and consensus algorithms on the extrachain are presented. Thirdly, both the extrachain selection algorithm and appending algorithm are proposed, so that the extrachain can be appended to the blockchain fairly and safely. Finally, an extrachain transmission scheme is presented to broadcast the blocks generated in the delayed network to the normal network. Theoretical analysis and simulation experiments further illustrate the efficiency of the proposed mechanism.

As a distributed learning paradigm, federated learning can be effectively applied to the decentralized system since it can resolve the “data island” problem. However, it is also vulnerable to serious privacy breaches. Although existing secure aggregation technique can address privacy concerns, they also incur significant additional computation and communication costs. To address these challenges, this paper offers a Communication Efficient Secure Aggregation scheme. Firstly, the central server uses the communication delay between terminals as the weight of the fully terminal-connected graph to transform it into a sparse connected graph based on the minimal spanning tree. Secondly, instead of relying on central server for key advertisement, the terminals advertise keys via a neighboring terminal forwarding approach based on sparsely graph. Thirdly, we propose using the central server for auxiliary advertising to address unexpected terminal dropout. Simultaneously, we theoretically demonstrate our scheme’s security and have lower computation and communication costs. Experiments show that CESA can reduce the running time by 28.2% without sacrificing security and model accuracy compared to conventional secure aggregation when there are 10 terminals in the system.

The security issues of the core (operating systems) of the Internet of Things (IoT) are becoming increasingly urgent and prominent, this article conducts a systematic research and summary of the security of the current mainstream IoT operating system. Firstly, based on the architecture and applications functions of IoT devices, this article introduces the concept of operating system security, analyzes and studies the security vulnerabilities, key technologies, and attack and defense security mechanisms of operating systems. Secondly, this article investigates the application scenario used by IoT operating systems, such as smart homes, smart healthcare, smart industries, blockchain, and the Internet of Vehicles. Next, from the perspective of building a complete security system, this article investigates the security mechanisms, security frameworks, security kernels, platform integrity, and security testing of IoT operating systems. Finally, this article points out the security challenges and opportunities faced by IoT operating systems, summarizes the current research status, and puts forward corresponding suggestions.

The widespread adoption of the Internet of Things (IoT) and deep learning (DL) have facilitated a social paradigm shift towards smart cities, accelerating the rapid construction of smart facilities. However, newly constructed facilities often lack the necessary data to learn any predictive models, preventing them from being truly smart. Additionally, data collected from different facilities is heterogeneous or may even be privacy-sensitive, making it harder to train proactive maintenance management (PMM) models that are robust to provide services across them. These properties impose challenges that have not been adequately addressed, especially at the city level. In this paper, we present a privacy-preserving, federated learning (FL) framework that can assist management personnel to proactively manage the maintenance schedule of IoT-empowered facilities in different organizations through analyzing heterogeneous IoT data. Our framework consists of (1) an FL platform implemented with fully homomorphic encryption (FHE) for training DL models with time-series heterogeneous IoT data and (2) an FL-based long short-term memory autoencoder model, namely FedLSTMA, for facility-level PMM. To evaluate our framework, we did extensive simulations with real-world data harvested from IoT-empowered public toilets, demonstrating that the DL-based FedLSTMA outperformed other traditional machine learning (ML) algorithms and had a high level of generalizability and capabilities of transferring knowledge from existing facilities to newly constructed facilities under the situation of huge data heterogeneity. We believe that our framework can be a potential solution for overcoming the challenges inherent in managing and maintaining other smart facilities, ultimately contributing to the effective realization of smart cities.

In the ever-changing world of technology, continuous authentication and comprehensive access management are essential during user interactions with a device. Split Learning (SL) and Federated Learning (FL) have recently emerged as promising technologies for training a decentralized Machine Learning (ML) model. With the increasing use of smartphones and Internet of Things (IoT) devices, these distributed technologies enable users with limited resources to complete neural network model training with server assistance and collaboratively combine knowledge between different nodes. In this study, we propose combining these technologies to address the continuous authentication challenge while protecting user privacy and limiting device resource usage. However, the model’s training is slowed due to SL sequential training and resource differences between IoT devices with different specifications. Therefore, we use a cluster-based approach to group devices with similar capabilities to mitigate the impact of slow devices while filtering out the devices incapable of training the model. In addition, we address the efficiency and robustness of training ML models by using SL and FL techniques to train the clients simultaneously while analyzing the overhead burden of the process. Following clustering, we select the best set of clients to participate in training through a Genetic Algorithm (GA) optimized on a carefully designed list of objectives. The performance of our proposed framework is compared to baseline methods, and the advantages are demonstrated using a real-life UMDAA-02-FD face detection dataset. The results show that CRSFL, our proposed approach, maintains high accuracy and reduces the overhead burden in continuous authentication scenarios while preserving user privacy.

3D naked-eye is constructed from multi-stream as a typical representation of stereoscopic video. Its enormous data volume and stringent low-delay transport requirements pose significant challenges for high-quality real-time transport. Through analysis and experimental verification that current streaming media transport frameworks using the server–client or peer-to-peer scheme face difficulties when transmitting 3D naked-eye in a one-to-one format. Besides, the existing bandwidth estimation algorithms cannot achieve the expected performance when dealing with delay-sensitive traffic. This results in low bandwidth utilization and slow bandwidth estimation, rendering it unfeasible to deliver multi-stream on time. We propose an effective transport framework with different modules for real-time multi-stream and introduce an Agent-to-Agent transport scheme that provides many-to-one connection as the main implementation way of 3D naked-eye transport framework. Additionally, we propose a direct bandwidth estimation algorithm to quickly match network bandwidth for low-delay transport. The Agent terminal centrally processes consolidates transports, and provides macro-level management of multiple video streams. The algorithm directly detects the available bandwidth using packet interval and packet rate models. Finally, using rate decision algorithm arbitrates the results to directly measure the maximum available bandwidth of the link. The Agent-to-Agent achieves 99% bandwidth utilization, addressing the limitations of existing streaming schemes in handling concurrent data streams. Our algorithm provides precise bandwidth estimates with minimal time overhead, meeting the requirements of a delay-sensitive 3D naked-eye system across diverse environments.

Smart contracts are self-executing digital agreements that automatically enforce the terms between parties, playing a crucial role in blockchain systems. However, due to the potential losses of digital assets caused by vulnerabilities, the security issues of Ethereum smart contracts have garnered widespread attention. To address this, researchers have developed various techniques to detect vulnerabilities in smart contracts, with fuzzing techniques achieving promising results. Nonetheless, current fuzzers are unable to effectively exercise suspicious targets because they overlook two key factors: comprehensively exploring all paths to the targets and providing high-quality directed seed inputs. This paper presents a Directed vulnerability veriFier (DFier), which elaborates effective transaction sequences with directed inputs for the fuzzer. This focuses on exploring target paths and automatically validating whether the specified locations are vulnerable. Specifically, DFier employs static analysis to help locate target paths, facilitating their comprehensive exploration. Additionally, we devise three heuristic strategies to enable our fuzzing technique to generate directed inputs that effectively validate the targets. Extensive experiments demonstrate that DFier is effective in verifying contract security, compared with three existing contract fuzzers (i.e., contractFuzzer, sFuzz, and conFuzzius), while the performance losses are in an acceptable range.

Hybrid Software Defined Networks (Hybrid SDNs), which combines the robustness of distributed network and the flexibility of centralized network, is now a prevailing network architecture. Previous hybrid SDN Traffic Engineering (TE) solutions search an optimal link weight setting or compute the splitting ratios of traffic leveraging heuristic algorithms. However, these methods cannot react timely to the fluctuating traffic demands in dynamic environments and suffer a hefty performance degradation when traffic demands change or network failures happen, especially when network scale is large. To cope with this, we propose a Multi-Agent reinforcement learning based TE method MATE that timely determines the route selection for network flows in dynamic hybrid SDNs. Through dividing the large-scale routing optimization problem into small-scale problem, MATE can better learn the mapping between the traffic demands and routing policy, and efficiently make online routing inference with dynamic traffic demands. To collaborate multiple agents and speed up the convergence in the training process, we innovatively design the actor network and introduce previous actions of all agents in the training of each agent. Extensive experiments conducted on different network topologies demonstrate our proposed method MATE has superior TE performance with dynamic traffic demands and is robust to network failures.