Federated Learning (FL) enables devices to collaboratively train machine learning models without sharing raw data, promoting privacy-preserving AI. However, practical deployment faces challenges in balancing the data privacy, communication overhead, and the training convergence rate. For instance, adding noise to local models to preserve privacy can increase the size of updates, exacerbating communication overhead and reducing the convergence rate, while coarse quantization reduces communication costs but can degrade model accuracy. This paper introduces a novel integration of diverse quantization schemes, including both uniform and adaptive quantization, synergistically paired with additive noise mechanisms, to optimally trade off the model/training precision/rate, communication overhead, and privacy protection. By adapting quantization levels based on training dynamics, including gradient variance and model convergence, our approach minimizes the learning error upper bound while ensuring theoretically quantified differential privacy and achieves significant savings in the number of communicated bits. To the best of our knowledge, this is the first work to integrate adaptive quantization with additive noise in FL. More importantly, we provide theoretical guarantees for differential privacy and convergence of the proposed framework and empirically evaluate its communication privacy tradeoffs. Experimental results on popular datasets like MNIST, CIFAR demonstrate that our method enables the training of convolutional neural networks with less than 4-bit quantization, achieving privacy budgets as low as 1.0, while maintaining accuracy that approaches the standard, non-differentially private FedAvg algorithm.

In this paper, we propose an effective blockchain-enabled information management framework, named Smart Blockchain-based Web 3.0 (SBW 3.0). Our framework aims to handle information within Web 3.0 efficiently, enhance data security and privacy, create new revenue streams, and encourage users to contribute valuable information to websites. To this end, SBW 3.0 employs blockchain technology and smart contracts to manage the decentralized data collection in Web 3.0. Moreover, we introduce a robust consensus mechanism grounded in Delegated Proof-of-Stake (DPoS) to reward user contributions. Furthermore, we develop a non-cooperative game model to examine user behavior in this context and conduct thorough analysis to prove the uniqueness of the Nash equilibrium in our proposed system. Through simulations, we evaluate the performance of SBW 3.0 and analyze the effects of various critical parameters on information contribution. Our results validate the theoretical analysis, showing that the proposed consensus mechanism successfully encourages nodes and users to provide more information, thus overcoming the current limitations of Web 3.0 regarding data decentralization and management.

This paper presents PP-AICloud, a practical system prototype designed to enable privacy-preserving AI inference for cloud-based mobile services. Motivated by recent industry efforts, such as Apple's integration of Homomorphic Encryption (HE) for on-device intelligence, our work addresses the key limitations of existing privacy-preserving machine learning (PPML) solutions, i.e., high latency, bandwidth inefficiencies, and excessive on-device computation. PP-AICloud leverages edge nodes as an intermediate computing layer between mobile devices and centralized AICloud infrastructures, distributing the HE workflow across edge and cloud resources. By integrating HE with deep convolutional neural networks (CNNs), the system enables efficient and secure inference on encrypted user data without requiring decryption. Experimental results demonstrate that PP-AICloud achieves more than 91% accuracy on a real-world landmark recognition task with real-time latency of under 0.7 seconds. We demonstrate the capabilities of PP-AICloud through demo videos available at: Demo link.

This work proposes a novel privacy-preserving cyberattack detection framework for blockchain-based Internet of Things (IoT) systems. In our approach, artificial intelligence (AI)-driven detection modules are strategically deployed at blockchain nodes (BNs) to identify real-time attacks, ensuring high accuracy and minimal delay. To achieve this efficiency, the model training is conducted by a cloud service provider (CSP). Accordingly, BNs send their data to the CSP for training, but to safeguard privacy, the data is encrypted using homomorphic encryption (HE) before transmission. This encryption method allows the CSP to perform computations directly on encrypted data without the need for decryption, preserving data privacy throughout the learning process. To handle the substantial volume of encrypted data, we introduce an innovative packing algorithm in a single-instruction-multiple-data (SIMD) manner, enabling efficient training on HE-encrypted data. Building on this, we develop a novel deep neural network training algorithm optimized for encrypted data. We further propose a privacy-preserving distributed learning approach based on the FedAvg algorithm, which parallelizes the training across multiple workers, significantly improving computation time. Upon completion, the CSP distributes the trained model to the BNs, enabling them to perform real-time, privacy-preserved detection. Our simulation results demonstrate that our proposed method can not only mitigate the training time but also achieve detection accuracy that is approximately identical to the approach without encryption, with a gap of around 0.01%. Additionally, our real implementations on various blockchain consensus algorithms and hardware configurations show that our proposed framework can also be effectively adapted to real-world systems.

In this work, we propose a novel machine learning empowered intrusion detection for Mobile Edge Computing (MEC) networks. Unlike most of the research works that focus on detecting attacks at the network layer, such as IP spoofing and Denial of Service (DoS) attacks, we aim to detect attacks/threats at the application layer, especially attacks caused by malicious codes embedded in offloaded computing tasks. This is an emerging issue in MEC networks as more and more MEC services allow MEC users to offload their computational tasks to the edge nodes to process. Yet, this is a very challenging problem in MEC, as data at the application layer is often complex and challenging to interpret, making anomaly detection difficult. Therefore, we first propose an effective solution to transfer data from the original offloading file to a new form, i.e., images, to make it more effective for the detection process. After that, a Convolutional Neural Network (CNN) and a collaborative learning process are proposed to learn information from training data (i.e., transformed images) and, at the same time, share the learned knowledge (i.e., trained models) together to improve the global accuracy in detecting attacks. Simulation results show that our approach can detect attacks with an accuracy of approximately 90%.

Web 3.0 is the third generation of the World Wide Web (WWW), concentrating on the critical concepts of decentralization, availability, and increasing client usability. Although Web 3.0 is undoubtedly an essential component of the future Internet, it currently faces critical challenges, including decentralized data collection and management. To overcome these challenges, blockchain has emerged as one of the core technologies for the future development of Web 3.0. In this paper, we propose a novel blockchain-based information management framework, namely Smart Blockchain-based Web (SBW), to manage information in Web 3.0 effectively, enhance the security and privacy of users’ data, bring additional profits, and incentivize users to contribute information to the websites. Particularly, SBW utilizes blockchain technology and smart contracts to manage the decentralized data collection process for Web 3.0 effectively. Moreover, in this framework, we develop an effective consensus mechanism based on Proof-of-Stake (PoS) to reward the user’s information contribution and conduct game theoretical analysis to analyze the user’s behavior in the considered system. Additionally, we conduct simulations to assess the performance of SBW and investigate the impact of critical parameters on information contribution. The findings confirm our theoretical analysis and demonstrate that our proposed consensus mechanism can incentivize the nodes and users to contribute more information to our systems.

This paper aims to propose a novel framework to address the data privacy issue for Federated Learning (FL)-based Intrusion Detection Systems (IDSs) in Internet-of-Vehicles (IoVs) with limited computational resources. In particular, in conventional FL systems, it is usually assumed that the computing nodes have sufficient computational resources to process the training tasks. However, in practical IoV systems, vehicles usually have limited computational resources to process intensive training tasks, compromising the effectiveness of deploying FL in IDSs. While offloading data from vehicles to the cloud can mitigate this issue, it introduces significant privacy concerns for vehicle users (VUs). To resolve this issue, we first propose a highly-effective framework using homomorphic encryption to secure data that requires offloading to a centralized server for processing. Furthermore, we develop an effective training algorithm tailored to handle the challenges of FL-based systems with encrypted data. This algorithm allows the centralized server to directly compute on quantum-secure encrypted ciphertexts without needing decryption. This approach not only safeguards data privacy during the offloading process from VUs to the centralized server but also enhances the efficiency of utilizing FL for IDSs in IoV systems. Our simulation results show that our proposed approach can achieve a performance that is as close to that of the solution without encryption, with a gap of less than 0.8%.

Federated Learning (FL) offers a privacy-preserving approach to training machine learning models from distributed data on resource-constrained devices. However, even for modern/high-end cars vehicular networks, onboard training with the whole of the raw data presents challenges due to limited computing capability and power consumption concerns. To address this conundrum, we propose a novel FL framework that leverages homomorphic encyption (HE) to allow vehicles to upload encrypted portions of their data to a cloud server. Thanks to the key feature of HE, the server can perform additional model updates directly on the encrypted data, alleviating the workload on vehicles while preserving privacy. Furthermore, model updates from vehicles are also HE-encrypted, guaranteeing end-to-end privacy protection. This approach reduces the computational burden on vehicles while maintaining the model quality and convergence performance of the FL framework. Additionally, it can mitigate biases stemming from heterogeneous data, resulting in more stable FL convergence. Extensive experiments demonstrate the effectiveness of our framework in reducing workload and improving learning stability in vehicular networks.

Federated Learning (FL) plays a pivotal role in enabling artificial intelligence (AI)-based mobile applications in mobile edge computing (MEC). However, due to the resource heterogeneity among participating mobile users (MUs), delayed updates from slow MUs may deteriorate the learning speed of the MEC-based FL system, commonly referred to as the straggling problem. To tackle the problem, this work proposes a novel privacy-preserving FL framework that utilizes homomorphic encryption (HE) based solutions to enable MUs, particularly resource-constrained MUs, to securely offload part of their training tasks to the cloud server (CS) and mobile edge nodes (MENs). Our framework first develops an efficient method for packing batches of training data into HE ciphertexts to reduce the complexity of HE-encrypted training at the MENs/CS. On that basis, the mobile service provider (MSP) can incentivize straggling MUs to encrypt part of their local datasets that are uploaded to certain MENs or the CS for caching and remote training. However, caching a large amount of encrypted data at the MENs and CS for FL may not only overburden those nodes but also incur a prohibitive cost of remote training, which ultimately reduces the MSP’s overall profit. To optimize the portion of MUs’ data to be encrypted, cached, and trained at the MENs/CS, we formulate an MSP’s profit maximization problem, considering all MUs’ and MENs’ resource capabilities and data handling costs (including encryption, caching, and training) as well as the MSP’s incentive budget. We then show that the problem is convex and can be efficiently solved using an interior point method. Extensive simulations on a real-world human activity recognition dataset show that our proposed framework can achieve much higher model accuracy (improving up to 24.29%) and faster convergence rate (by 2.86 times) than those of the conventionalFedAvgapproach when the straggling probability varies between 20% and 80%. Moreover, the proposed framework can improve the MSP’s profit up to 2.84 times compared with other baseline FL approaches without MEN-assisted training.

Measurement data from wireless sensors deployed in large agricultural areas could be used to help the automation of precision farming activities such as irrigation management, fertilization, etc. The widespread use of sensors with limited battery capacity in precision farming largely depends on data collection methods that reduce the energy consumption of transmitting measurement data and prolong the battery run time. In this article, we investigate joint clustering and multi-UAV-assisted data-gathering schemes to save the energy consumption of sensors. We establish a theoretical lower bound for the energy consumption of sensors to transport data to cluster heads and prove that the energy consumption of sensors approaches the theoretical lower bound if clusters are balanced regarding energy consumption. Therefore, the essential step of proposed heuristic multi-UAV schemes, calledGathering data Assisted by Multi-UAV with a BAlanced Clustering(GAMBAC), is to find balanced or near-balanced clusters concerning energy consumption. For sensor networks with a small number of nodes our heuristic algorithms give results close to the ones obtained by the reference solution. Numerical results show that the GAMBAC schemes extend network lifetime and requires less energy to support a specific number of collection rounds than the best existing approach. Numerical results show that the GAMBAC schemes extend network lifetime and requires less energy to support a specific number of collection rounds than the best existing approach. Therefore, the GAMBAC algorithms could enhance the reliable data collection of sensor networks for precision farming.

Abstract A quest for geographic routing schemes of wireless sensor networks when sensor nodes are deployed in areas with obstacles has resulted in numerous ingenious proposals and techniques. However, there is a lack of solutions for complicated cases wherein the source or the sink nodes are located close to a specific hole, especially in cavern-like regions of large complex-shaped holes. In this paper, we propose a geographic routing scheme to deal with the existence of complicated-shape holes in an effective manner. Our proposed routing scheme achieves routes around holes with the (1+ $$\epsilon$$ ϵ )-stretch. Experimental results show that our routing scheme yields the highest load balancing and the most extended network lifetime compared to other well-known routing algorithms as well.