Implementation of Secure and Privacy-aware AI Hardware using Distributed Federated Learning

In this paper, the convergence time of federated learning (FL), when deployed over a realistic wireless network, is studied. In particular, a wireless network is considered in which wireless users transmit their local FL models (trained using their locally collected data) to a base station (BS). The BS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all users. Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected to transmit their local FL model parameters to the BS at each learning step. Moreover, since each user has unique training data samples, the BS prefers to include all local user FL models to generate a converged global FL model. Hence, the FL training loss and convergence time will be significantly affected by the user selection scheme. Therefore, it is necessary to design an appropriate user selection scheme that can select the users who can contribute toward improving the FL convergence speed more frequently. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize the FL convergence time and the FL training loss. To solve this problem, a probabilistic user selection scheme is proposed such that the BS is connected to the users whose local FL models have significant effects on the global FL model with high probabilities. Given the user selection policy, the uplink RB allocation can be determined. To further reduce the FL convergence time, artificial neural networks (ANNs) are used to estimate the local FL models of the users that are not allocated any RBs for local FL model transmission at each given learning step, which enables the BS to improve the global model, the FL convergence speed, and the training loss. Simulation results show that the proposed approach can reduce the FL convergence time by up to 56% and improve the accuracy of identifying handwritten digits by up to 3%, compared to a standard FL algorithm.

Artificial intelligence has significantly enhanced disease diagnosis in healthcare, particularly through Deep Learning (DL) and Federated Learning (FL) approaches. These technologies have shown promise in detecting ocular diseases using medical imaging while addressing challenges related to data privacy and security. FL enables collaborative learning without sharing sensitive medical data, making it an attractive solution for healthcare applications. This systematic review aims to analyze the advancements in AI-driven ocular disease detection, with a particular focus on FL-based approaches. The article evaluates the evolution, methodologies, challenges, and effectiveness of FL in enhancing diagnostic accuracy while ensuring data confidentiality. The systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework to ensure transparency and reliability. Research articles published between 2017 and 2024 were identified using academic databases, including Web of Science, Scopus, IEEE Xplore, and PubMed. Studies focusing on DL and FL models for detecting ocular diseases were selected based on predefined inclusion and exclusion criteria. A comparative analysis of the methodologies, architectures, datasets, and performance metrics of different FL models has been presented. The findings indicated that FL preserves data privacy while achieving diagnostic performance comparable to traditional centralized AI models. Various FL models, including FedAvg and FedProx, have been implemented for ocular disease detection, with high accuracy and efficiency. However, challenges, such as data heterogeneity, communication efficiency, and model convergence, persist. FL represents a promising approach for ocular disease detection, balancing diagnostic accuracy with data privacy. Future research may focus on optimizing FL frameworks for improving scalability, communication efficiency, and integrating advanced privacy-preserving techniques.

The trade-off between privacy and accuracy presents a challenge for current federated learning (FL) frameworks, hindering their progress from theory to application. The main issues with existing FL frameworks stem from a lack of interpretability and targeted privacy protections. To cope with these, we proposed Disentangled Federated Learning for Privacy (DFLP) which employes disentanglement, one of interpretability techniques, in private FL frameworks. Since sensitive properties are client-specific in nature, our main idea is to turn this feature into a tool that strikes the balance between data privacy and FL model performance, enabling the sensitive attributes to be private. DFLP disentangles the client-specific and class-invariant attributes to mask the sensitive attributes precisely. To our knowledge, this is the first work that successfully integrates disentanglement and the nature of sensitive attributes to achieve privacy protection while ensuring high FL model performance. Extensive experiments validate that disentanglement is an effective method for accuracy-aware privacy protection in FL frameworks.

In this paper, the optimization of network performance to support the deployment of federated learning (FL) is investigated. In particular, in the considered model, each user owns a machine learning (ML) model by training through its own dataset, and then transmits its ML parameters to a base station (BS) which aggregates the ML parameters to obtain a global ML model and transmits it to each user. Due to limited radio frequency (RF) resources, the number of users that participate in FL is restricted. Meanwhile, each user uploading and downloading the FL parameters may increase communication costs thus reducing the number of participating users. To this end, we propose to introduce visible light communication (VLC) as a supplement to RF and use compression methods to reduce the resources needed to transmit FL parameters over wireless links so as to further improve the communication efficiency and simultaneously optimize wireless network through user selection and resource allocation. This user selection and bandwidth allocation problem is formulated as an optimization problem whose goal is to minimize the training loss of FL. We first use a model compression method to reduce the size of FL model parameters that are transmitted over wireless links. Then, the optimization problem is separated into two subproblems. The first subproblem is a user selection problem with a given bandwidth allocation, which is solved by a traversal algorithm. The second subproblem is a bandwidth allocation problem with a given user selection, which is solved by a numerical method. The ultimate user selection and bandwidth allocation are obtained by iteratively compressing the model and solving these two subproblems. Simulation results show that the proposed FL algorithm can improve the accuracy of object recognition by up to 16.7% and improve the number of selected users by up to 68.7%, compared to a conventional FL algorithm using only RF.

Federated learning (FL) has become an emerging distributed framework to build deep learning models with collaborative efforts from multiple participants. Consequently, copyright protection of FL deep model is urgently required because too many participants have access to the joint-trained model. Recently, Secure FL framework is developed to address data leakage issue when central node is not fully trustable. This encryption process has made existing DL model watermarking schemes impossible to embed watermark at the central node. In this paper, we propose a novel client-side Federated Learning watermarking method to tackle the model verification issue under the Secure FL framework. In specific, we design a backdoor-based watermarking scheme to allow model owners to embed their pre-designed noise patterns into the FL deep model. Thus, our method provides reliable copyright protection while ensuring the data privacy because the central node has no access to the encrypted gradient information. The experimental results have demonstrated the efficiency of our method in terms of both FL model performance and watermarking robustness.

With the growth of participating clients, the centralized parameter server (PS) will seriously limit the scale and efficiency of Federated Learning (FL). A straightforward approach to scale up the FL system is to construct a Parallel FL (PFL) system with multiple parallel PSes. However, it is unclear whether PFL can really accelerate FL or reduce the training time of FL. Even if the answer is yes, it is non-trivial to design a highly efficient parameter average algorithm for a PFL system. In this paper, we propose a completely parallelizable FL algorithm called P-FedAvg under the PFL architecture. P-FedAvg extends the well-known FedAvg algorithm by allowing multiple PSes to cooperate and train a learning model together. In P-FedAvg, each PS is only responsible for a fraction of total clients, but PSes can mix model parameters in a dedicatedly designed way so that the FL model can well converge. Different from heuristic-based algorithms, P-FedAvg is with theoretical guarantees. To be rigorous, we theoretically analyze the convergence rate of P-FedAvg in terms of the number of conducted iterations, the communication cost of each global iteration and the optimal weights for each PS to mix parameters with its neighbors. Based on theoretical analysis, we conduct a case study on five typical overlay topolgoies formed by PSes to further examine the communication efficiency under different topologies, and investigate how the overlay topology affects the convergence rate, communication cost and robustness of a PFL system. Lastly, we perform extensive experiments with real datasets to verify our analysis and demonstrate that P-FedAvg can significantly speed up FL than traditional FedAvg and other competitive baselines. We believe that our work can help to lay a theoretical foundation for building more efficient PFL systems.

A novel federated learning-based two-stage approach for ship energy consumption optimization considering both shipping data security and statistical heterogeneity

Federated Learning (FL) has recently attracted great interest in sensor-based human activity recognition (HAR) tasks. However, in real-world environment, sensor data on devices is non-independently and identically distributed (Non-IID), e.g., activity data recorded by most devices is sparse, and sensor data distribution for each client may be inconsistent. As a result, the traditional FL methods in the heterogeneous environment may incur a drifted global model that causes slow convergence and a heavy communication burden. Although some FL methods are gradually being applied to HAR, they are designed for overly ideal scenarios and do not address such Non-IID problem in the real-world setting. It is still a question whether they can be applied to cross-device FL. To tackle this challenge, we propose ProtoHAR, a prototype-guided FL framework for HAR, which aims to decouple the representation and classifier in the heterogeneous FL setting efficiently. It leverages the global prototype to correct the activity feature representation to make the prototype knowledge flow among clients without leaking privacy while solving a better classifier to avoid excessive drift of the local model in personalized training. Extensive experiments are conducted on four publicly available datasets: USC-HAD, UNIMIB-SHAR, PAMAP2, and HARBOX, which are collected in both controlled environments and real-world scenarios. The results show that compared with the state-of-the-art FL algorithms, ProtoHAR achieves the best performance and faster convergence speed in HAR datasets.

The convergence of vehicular technology, artificial intelligence (AI), and distributed computing has catalyzed the emergence of the Internet of Vehicles (IoV) as a cornerstone of next-generation intelligent transportation systems (ITS). By enabling vehicle-to-everything (V2X) communication, IoV supports cooperative perception, real-time decision-making, and autonomous driving. However, the reliance on large-scale, data-driven intelligence in IoV exposes systems to critical challenges, including adversarial poisoning, privacy leakage, identity forgery, and the fragility of centralized learning architectures. Federated Learning (FL) has been proposed as a promising paradigm to alleviate some of these issues by enabling distributed model training without centralizing sensitive vehicular data. Nonetheless, conventional FL remains vulnerable to security and trust limitations, particularly in dynamic vehicular environments. This thesis addresses these challenges by designing secure, privacy-preserving, and scalable FL frameworks that leverage distributed ledger technologies and cutting-edge security mechanisms.The thesis advances knowledge through four interconnected contributions. First, two novel optimization-driven poisoning attack models are introduced: PA-PSOSA and PAPSOGA, which combine particle swarm optimization with simulated annealing and genetic algorithms, respectively. These models demonstrate that even a small poisoning budget can substantially degrade global model utility under black-box and clean-label constraints, highlighting the urgency of robust defenses in vehicular FL. Second, a permissioned blockchain-enabled FL (BCFL) framework is proposed, in which consortium edge nodes running Practical Byzantine Fault Tolerance (PBFT) consensus replace the central aggregator. With blockchain integration and data validation mechanisms, this design ensures identity authentication, verifiable audit trails, and improved resilience against poisoning and Sybil attacks, while maintaining high model accuracy under adversarial conditions. Third, the framework is further enhanced to achieve inference-resistance by integrating secure aggregation (SecAgg) and differential privacy (DP), and lightweight with off-chain commitments. This design significantly reduces ledger storage requirements, increases system throughput, and mitigates inference-based privacy risks. Finally, to overcome the scalability limitations of PBFT-based BCFL, a DAG-enabled FL (DFL) framework is developed. By leveraging parallel validation, utility-score-based tip selection, and reputation-weighted aggregation, this framework significantly improves scalability, reduces communication complexity, and enhances robustness in asynchronous vehicular environments.Together, these contributions articulate a coherent progression from exposing vulnerabilities in vehicular FL to constructing secure, privacy-preserving, and scalable frameworks tailored for IoV ecosystems. The findings demonstrate that interdisciplinary integration of optimization theory, cryptography, differential privacy, and distributed ledger technologies is indispensable for trustworthy vehicular intelligence. Beyond theoretical significance, the proposed frameworks offer practical designs for deployment in safety-critical IoV environments. Future research directions include the integration of zero-knowledge proofs (ZKP) for verifiable privacy, adaptive defenses against evolving adversarial strategies, and experimental validation in real-world vehicular testbeds. Collectively, this thesis establishes a foundation for secure federated intelligence in IoV, contributing to the reliability, efficiency, and trustworthiness of next-generation ITS.

Federated learning (FL) offers an effective learning architecture to protect data privacy in a distributed manner. However, the inevitable network asynchrony, overdependence on a central coordinator, and lack of an open and fair incentive mechanism collectively hinder FL's further development. We propose IronForge, a new generation of FL framework, that features a directed acyclic graph (DAG)-based structure, where nodes represent uploaded models, and referencing relationships between models form the DAG that guides the aggregation process. This design eliminates the need for central coordinators to achieve fully decentralized operations. IronForge runs in a public and open network and launches a fair incentive mechanism by enabling state consistency in the DAG. Hence, the system fits in networks where training resources are unevenly distributed. In addition, dedicated defense strategies against prevalent FL attacks on incentive fairness and data privacy are presented to ensure the security of IronForge. Experimental results based on a newly developed test bed FLSim highlight the superiority of IronForge to the existing prevalent FL frameworks under various specifications in performance, fairness, and security. To the best of our knowledge, IronForge is the first secure and fully decentralized FL (DFL) framework that can be applied in open networks with realistic network and training settings.

Federated learning (FL), which enables multiple distributed devices (clients) to collaboratively train a global model without transmitting their private data, has attracted much attention in the Internet of Things (IoT) domain. Compared with centralized learning, FL has obvious privacy advantages because it can protect the clients’ raw data from direct access by adversaries. Furthermore, to prevent the adversaries from inferring private information from the transmitted parameters, several FL algorithms based on differential privacy (DP) have been proposed, where the clients add artificial noise to their local parameters for privacy protection. Nevertheless, the added noise would disrupt the learning process and degrade the performance of the trained model. Considering this, in this article, we develop a performance-enhanced DP-based FL (PEDPFL) algorithm, where a classifier-perturbation regularization method is proposed to improve the robustness of the trained model against DP-injected noise. We derive the theoretical privacy and convergence analysis of the proposed algorithm, and also demonstrate the influence of some hyperparameters on the convergence performance. Simulation results on real-world data sets show that the proposed algorithm has better classification performance than the existing DP-based FL algorithms at the same level of privacy protection, and thus, it is more applicable to IoT applications.

Federated learning is a type of distributed machine learning that focuses on solutions for the properties of training data on edge devices as well as the privacy of the training set. Federated learning is a discipline highly relevant to real-world applications, and thus the emphasis on different perspectives requires an adaptation of the federated learning framework. Although almost every newly proposed federated learning algorithm is compared with some existing algorithms, current research on testing comparisons between commonly used federated learning algorithms remains vague and complex. Therefore, the purpose of this paper is to test and compare several federated learning frameworks, including the representative FedAvg, MOON, FedProx, and MOON. Based on revisiting the theory and key steps of these algorithms, an analysis of the performance performance will be conducted, evaluating their advantages for applications. Furthermore, a summary based on the test results will be provided, pointing out possible future challenges as well as research directions.

<abstract><p>Federated learning (FL) has attracted a lot of interests as a promising machine learning approach to protect user privacy and data security. It requires the clients to send model parameters to the server rather than private datasets, thus protecting privacy to a significant extent. However, there are several types of heterogeneities (data, model, objective and systems) in FL scenario, posing distinct challenges to the canonical FL algorithm (FedAvg). In this work, we propose a novel FL framework that integrates knowledge distillation and Bayesian inference to address this multi-dimensional heterogeneity problem. On the client side, we approximate the local likelihood function using a scaled multi-dimensional Gaussian probability density function (PDF). Moreover, each client is allowed to design customized model according to the requirement through knowledge distillation. On the server side, a multi-Gaussian product mechanism is employed to construct and maximize the global likelihood function, greatly enhancing the accuracy of the aggregated model in the case of data heterogeneity. Finally, we show in extensive empirical experiments on various datasets and settings that global model and local model can achieve better performance and require fewer communication rounds to converge compared with other FL techniques.</p></abstract>

Federated learning (FL) is a promising machine learning paradigm that focuses on sending data to the client, then using the local unique data to train the local model. Only the model updates are sent back to be aggregated into a global model; this action can efficiently protect the data privacy and security. However, developing the FL model in the real world is still unreliable due to the problem that the real-world dataset always contains both desired in-distribution data and unexpected out-of-distribution (OOD) data. Current FL researchers typically use prefabricated artificial data sets to conduct a series of experiments and obtain positive results, yet most of these datasets are in-distribution data. In this work, we propose a light weight Client-Side OOD Filtering method tailored for real-world FL compatibility. This method integrates seamlessly with standard FL frameworks by adding a simple pre-processing step on the client side, without modifying server-side aggregation logic. The core design includes two key components: (1) A lightweight ID classifier that quantifies the alignment between local data and ID distribution with soft max probability. (2) An adaptive threshold mechanism that retains data with probability ≥ IID data for regional training and filters out low probability data.

Federated Learning (FL) is a Machine Learning (ML) paradigm in which multiple devices collaboratively train a model without sharing their local data. This decentralized approach provides significant privacy benefits, enabling compliance with data protection regulations and safeguarding sensitive user information by keeping raw data on local devices. Instead of transmitting raw data, FL sends model updates to a central aggregator to improve the global model. However, this process can result in higher Carbon Dioxide (CO₂) emissions compared to traditional centralized ML systems, due to the increased number of participating devices and communication rounds. This study evaluates the performance, convergence speed, energy efficiency, and environmental impact of FL models compared to centralized models, using the Modified National Institute of Standards and Technology dataset (MNIST) and Canadian Institute for Advanced Research-10 classes dataset (CIFAR-10). Four models were tested: two FL models and two centralized models. The evaluation focused on accuracy, number of training rounds to convergence, and total CO₂ emissions. To optimize both convergence and energy efficiency, a dynamic hill-climbing-based early stopping technique was introduced. After every 100 rounds, model accuracy improvements were assessed, and training was terminated early if further gains fell below a shrinking threshold, effectively reducing unnecessary computation and energy consumption. Results show that, under the tested conditions, FL models achieved competitive or higher accuracy than centralized models, particularly on non-Independent and Identically Distributed (IID) data distributions. For example, the federated MNIST model reached 98.79% accuracy with a significantly lower carbon footprint when early stopping was applied. Overall, the proposed optimization approach reduced CO₂ emissions by approximately 60% without substantial loss in accuracy. By integrating privacy preservation, explicit regulatory relevance, and a practical dynamic optimization method, this research demonstrates that FL can deliver strong model performance while meeting modern requirements for data privacy and environmental sustainability