Neural networks (NN) have demonstrated considerable capabilities in tackling tasks in a diverse set of fields, including natural language processing, image classification, and regression. In recent years, the amount of available data to train Deep Learning (DL) models has increased tremendously, thus requiring larger and larger models to learn the underlying patterns in the data. Inference time, communication cost in the distributed case, required storage resources, and computational capabilities have increased proportional to the model's size, thus making NNs less suitable for two cases: i) tasks requiring low inference time (e.g., real-time monitoring) and ii) training on low powered devices. These two cases, which have become crucial in the last decade due to the pervasiveness of low-powered devices and NN models, are addressed in this licentiate thesis. As the first contribution, we analyze the distributed case with multiple low-powered devices in a federated scenario. Cross-device Federated Learning (FL) is a branch of Machine Learning (ML) where multiple participants train a common global model without sharing data in a centralized location. In this thesis, a novel technique named Coded Federated Dropout (CFD) is proposed to carefully split the global model into sub-models, thus increasing communication efficiency and reducing the burden on the devices with only a slight increase in training time. We showcase our results for an example image classification task. As the second contribution, we consider the anomaly detection task on Electrocardiogram (ECG) recordings and show that including prior knowledge in NNs models drastically reduces model size, inference time, and storage resources for multiple state-of-the-art NNs. In particular, this thesis focuses on AEs, a subclass of NNs, which is suitable for anomaly detection. I propose a novel approach, called FMM-Head, which incorporates basic knowledge of the ECG waveform shape into an AE. The evaluation shows that we improve the AUROC of baseline models while guaranteeing under-100ms inference time, thus enabling real-time monitoring of ECG recordings from hospitalized patients. Finally, several potential future works are presented. The inclusion of prior knowledge can be further exploited in the ECG Imaging (ECGI) case, where hundreds of ECG sensors are used to reconstruct the 3D electrical activity of the heart. For ECGI, the reduction in the number of sensors employed (i.e., the input space) is also beneficial in terms of reducing model size. Moreover, this thesis advocates additional techniques to integrate ECG anomaly detection in a distributed and federated case. / Neurala nätverk (NN) har visat god förmåga att tackla uppgifter inom en mängd olika områden, inklusive Natural Language Processing (NLP), bildklassificering och regression. Under de senaste åren har mängden tillgänglig data för att träna Deep Learning (DL)-modeller ökat enormt, vilket kräver större och större modeller för att lära sig de underliggande mönstren i datan. Inferens tid och kommunikationskostnad i det distribuerade fallet, nödvändiga lagringsresurser och beräkningskapacitet har ökat proportionerligt mot modellens storlek vilket gör NN mindre lämpliga använda i två fall: (i) uppgifter som kräver snabba slutledningar (t.ex. realtidsövervakning) och (ii) användning på mindre kraftfulla enheter. De här två fallen, som har blivit mer förekommande under det senaste decenniet på grund av omfattningen av mindre kraftfulla enheter och NN-modeller, behandlas i denna licentiatuppsats. Som det första bidraget analyserar vi det distribuerade fallet med flera lättdrivna enheter i ett federerat scenario. Cross-device Federated Learning (FL) är en gren av Machine Learning (ML) där flera deltagare tränar en gemensam global modell utan att dela data på en centraliserad plats. I denna avhandling föreslås en nyteknik, Coded Federated Dropout (CFD), som delar upp den globala modellen i undermodeller, vilket ökar kommunikationseffektiviteten och samtidigt minskar belastningen på enheterna. Detta erhålls med endast en liten förlängning av träningstiden. Vi delger våra resultat för en exempeluppgift för bildklassificering. Som det andra bidraget betraktar vi anomalidetekteringsuppgiften Elektrokardiogram (EKG)-registrering och visar att inklusionen av förkunskaper i NN-modeller drastiskt minskar modellstorlek, inferenstider och lagringsresurser för flera moderna NN. Speciellt fokuserar denna avhandling på Autoencoders (AEs), en delmängd av NN, lämplig för avvikelsedetektering. En ny metod, kallad FMM-Head, föreslås. vilken  omformar grundläggande kunskaper om EKG-vågformen till en AE. Utvärderingen visar att vi förbättrar arean under kurvan (AUROC) för baslinjemodeller samtidigt som vi garanterar under 100 ms inferenstid, vilket möjliggör realtidsövervakning av EKG-inspelningar från inlagda patienter.  Slutligen presenteras flera potentiella framtida utvidgningar. Införandet av tidigare kunskap kan utnyttjas ytterligare i fallet med EKG Imaging (ECGI), där hundratals EKG-sensorer används för att rekonstruera den elektriska 3D-aktiviteten hos hjärtat. För ECGI är minskningen av antalet använda sensorer (dvs inmatningsutrymme) också fördelaktig när det gäller att minska modellstorleken. Dessutom förespråkas i denna avhandling ytterligare tekniker för att integrera EKG-avvikelsedetektering i distribuerade och federerade fall. / <p>This research leading to this thesis is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Research Administration (ORA) under Award No. ORA-CRG2021-4699</p>

Federated learning is an emerging field that has received tremendous attention as it enables training Deep Neural Networks in a distributed fashion. By keeping the data decentralized, Federated Learning enhances data privacy and security while maintaining the ability to train robust machine learning models. Unfortunately, despite these advantages, the communication overhead resulting from the demand for fre- quent communication between the central server and remote clients poses a serious challenge to the present-day communication infrastructure. As the size of the deep learning models and the number of devices participating in the training are ever in- creasing, the model gradient transmission between the remote clients and the central server orchestrating the training process becomes the critical performance bottleneck. In this thesis, we investigate and address the problems related to improving the communication efficiency while maintaining convergence speed and accuracy in Federated Learning. To characterize the trade-off between communication cost and convergence in Federated Learning, an innovative formulation utilizing the clients’ correlation is proposed, which considers gradient transmission and reconstruction problems as a multi-terminal source coding problem. Leveraging this formulation, the model up- date problem in Federated Learning is converted to a convex optimization problem from a rate-distortion perspective. Technical results, including an iterative algorithm to solve for the upper bound and lower bound of the sum-rate, as well as the rate allocation schemes, are provided. Additionally, a correlation-aware client selection strategy is proposed and evaluated against the state-of-the-art methods. Extensive simulations are conducted to validate our theoretical analysis and the effectiveness of the proposed approaches. Furthermore, based on the statistical insights about the model gradient, we pro- pose a gradient compression algorithm also inspired by rate-distortion theory. More specifically, the proposed algorithm adopts model-wise sparsification for preliminary gradient dimension reduction and then performs layer-wise gradient quantization for further compression. The experimental results show that our approach achieves compression as aggressive as 1-bit while maintaining proper model convergence speed and final accuracy. / Thesis / Doctor of Science (PhD) / Federated Learning is a machine learning framework that allows remote clients to collaboratively train a model without raw data exchange, which ensures local data privacy. It differs from traditional machine learning scenarios where data needs to be stored centrally. This decentralized framework is advantageous in several respects including: data security, data diversity, real-time continual learning and hardware efficiency. However, the demand for frequent communication between clients and the server imposes tremendous communication challenges in applying Federated Learning to real-world scenarios. This thesis aims to tackle the problems in FL by theoretically characterizing the problem and developing practical methodologies. The theoretical results allow for systematic analysis of the communication cost and convergence rate. The experimental results validate the effectiveness of the proposed methods in improving communication efficiency and convergence in Federated Learning.

<p dir="ltr">In recent years, Federated Learning (FL) has emerged as a promising approach for training machine learning models across distributed data sources while preserving privacy. However, traditional FL faces significant challenges in reliabilities, including the risk of the single point of failure and vulnerabilities to adversarial attacks. </p><p dir="ltr">This research proposes an innovative framework, Blockchain-based FL(BCFL), leveraging blockchain to decentralize the FL system and enhance its reliability. To optimize BCFL in resource-constrained environments, we design incentive mechanisms and resource allocation schemes to maximize computational efficiency for clients engaging in both training and mining tasks. Additionally, we introduce a dual-task resource allocation scheme specifically tailored for Mobile Edge Computing (MEC), enabling edge servers to manage both BCFL and offloading tasks efficiently. To address the inherent risk of client dropout in distributed learning, we propose the HieAvg algorithm within a decentralized hierarchical FL framework, mitigating the impact of stragglers through historical weight-based aggregation. This research also introduces the Faker attack, a novel model poisoning approach that exploits weaknesses in similarity metrics commonly used in FL defenses. In response, we develop the Similarity of Partial Parameters (SPP) defense, a random parameter selection strategy that disrupts the predictability of similarity evaluations, offering robust protection against adaptive attacks.</p><p dir="ltr">Our research provides practical strategies to fortify FL systems against reliability vulnerabilities. This work lays the foundation for more secure, reliable, and efficient FL in various environments through decentralized architectures and novel fault </p>

Thesis (M.A.)--University of Hawaii at Manoa, 2007 / Pacific Islands Studies

The need for a method to create a collaborative machine learning model which can utilize data from different clients, each with privacy constraints, has recently emerged. This is due to privacy restrictions, such as General Data Protection Regulation, together with the fact that machine learning models in general needs large size data to perform well. Google introduced federated learning in 2016 with the aim to address this problem. Federated learning can further be divided into horizontal and vertical federated learning, depending on how the data is structured at the different clients. Vertical federated learning is applicable when many different features is obtained on distributed computation nodes, where they can not be shared in between. The aim of this thesis is to identify the current state of the art methods in vertical federated learning, implement the most interesting ones and compare the results in order to draw conclusions of the benefits and drawbacks of the different methods. From the results of the experiments, a method called FedBCD shows very promising results where it achieves massive improvements in the number of communication rounds needed for convergence, at the cost of more computations at the clients. A comparison between synchronous and asynchronous approaches shows slightly better results for the synchronous approach in scenarios with no delay. Delay refers to slower performance in one of the workers, either due to lower computational resources or due to communication issues. In scenarios where an artificial delay is implemented, the asynchronous approach shows superior results due to its ability to continue training in the case of delays in one or several of the clients.

För varje dag som går möter stora industrier en ökad mängd intrång i sina IT-system. De flesta befintliga verktyg som använder sig utav maskininlärning är starkt beroende av stora mängder data, vilket innebär risker under dataöverföringen. Därför har syftet med denna studie varit att undersöka om en decentraliserad integritetsbevarande strategi kan vara ett bra alternativ för att minska effektiviteten av dessa attacker. Mer specifikt skulle användningen av Random Forests, en av de mest populära algoritmerna för maskininlärning, kunna utökas med decentraliseringstekniken Federated Learning tisammans med Differential Privacy, för att skapa en ideal metod för att upptäcka nätverksintrång? Med hjälp av befintliga kodbibliotek för maskininlärnings och verklighetsbaserad data har detta projekt konstruerat olika modeller för att simulera hur väl olika decentraliserade och integritetsbevarande modeller kan jämföras med traditionella alternativ. De skapade modellerna innehåller antingen Federated Learning, Differential Privacy eller en kombination av båda. Huvuduppgiften för dessa modeller är att förbättra integriteten och samtidigt minimera minskningen av precision. Resultaten indikerar att båda teknikerna kommer med en liten minskning i noggrannhet jämfört med traditionella alternativ. Huruvida precisionsförlusten är acceptabel eller beror på det specifika användningsområdet. Det utvecklade kombinerade alternativet lyckades dock inte nå acceptabel precision vilket hindrar oss från att dra några slutsatser. / With each passing day, large industries face an increasing amount of intrusions into their IT environments. Most existing machine learning countermeasures heavily rely on large amounts of data which introduces risk during the data-transmission. Therefore, the objective of this study has been to investigate whether a decentralized privacy-preserving approach could be a sensible alternative to decrease the effectiveness of these attacks. More specifically could the use of Random Forests, one of the most popular machine learning algorithms, be extended using the decentralization technique Federated Learning in cooperation with Differential Privacy, in order to create an ideal approach for network intrusion detection? With the assistance of existing machine learning code-libraries and real-life data, this thesis has constructed various experimental models to simulates how well different decentralized and privacy-preserving approaches compare to traditional ones. The models created incorporate either Federated Learning, Differential Privacy or a combination of both. The main task of these models is to enhance privacy while minimizing the decrease in accuracy. The results indicate that both techniques comes with a small decrease in accuracy compared to traditional alternatives. whether the accuracy loss is acceptable or not may depend on the specific scenario. The developed combined approach however, failed to reach acceptable accuracy which prevents us from drawing any conclusions.

The increasing complexity of trading strategies, when combined with machine learning models, forces market surveillance corporations to develop increasingly sophisticated methods for recognizing potential misuse. One strategy is to employ traders’ weapons against themselves, namely machine learning. However, the data utilized in market surveillance is highly sensitive, what may be available for machine learning is limited. In this thesis, we examine how federated learning for time series data can be used to identify potential market abuse while maintaining client privacy and data security. We are interested in developing a time-series-specific neural network employing federated learning. We demonstrate that when this strategy is used, the performance of detecting potential market abuse is comparable to that of the standard data centralized approach. Specifically, a non-federated model, a federated model, and a federated model with extra data privacy and security protection are evaluated and compared. Each model utilize an LSTM autoencoder to identify market abuse. The results demonstrate that a federated model’s performance in detecting possible market abuse is comparable to that of a non-federated model. Moreover, a federated approach with extra data privacy and security experienced a slight performance loss but is still a competitive model in comparison to the other models. Although this approach results in increased privacy and security, there is a limit to how much privacy and security can be ensured, as excessive privacy led to extremely poor performance. Federated learning offers the ability to increase data privacy and security with little performance decrease. / Den ökande komplexiteten handelsstrategier, i kombination med maskininlärning modeller, tvingar marknadsövervakning företag att utveckla allt mer sofistikerade metoder för att identifiera potentiellt marknadsmissbruk. En strategi är att använda handlarnas vapen mot sig själva, nämligen maskininlärning. Däremot, data som används inom marknadsövervakning är mycket känslig och vad som kan finnas tillgängligt för maskininlärning är begränsat.I den här studien undersöker vi hur federerat lärande för tidsseriedata kan användas till att identifiera potentiellt marknadsmissbruk samtidigt som klienternas integritet och datasäkerhet bibehålls. Vi är intresserade av att utveckla ett tidsserie-specifikt neuralt nätverk med hjälp av federated inlärning. Vi visar att när denna strategi används är prestanda för att upptäcka potentiellt marknadsmissbruk jämförbart med det för den vanliga data-centraliserade metoden. Specifikt, en icke-federerad modell, en federerad modell och en federerad modell med extra dataintegritet och säkerhet utvärderas och jämförs. Varje modell använder en LSTM-Autoencoder för att identifiera marknadsmissbruk. Resultaten visar att en federerad modells prestanda när det gäller att upptäcka eventuellt marknadsmissbruk är jämförbar med en icke-federerad modell. Dessutom, ett federerat tillvägagångssätt med extra dataintegritet upplevde en liten prestandaförlust men är fortfarande en konkurrenskraftig modell i jämförelse med andra modeller. Även om detta tillvägagångssätt resulterar i ökad integritet och säkerhet, finns det en gräns för hur mycket som kan säkerställas. Federated learning möjliggör ökad datasekretess och säkerhet med liten prestandasänkning.

Detta arbete syftar till att undersöka effektiviteten av federated learning (FL) för bildklassificering i decentraliserade databehandlingsmiljöer. Med den ökande mängden av datagenerering från mobil- och ‘edge computing’, särskilt bilddata, så finns ett behov av att förbättra metoderna för bildklassificering. Dessa metoder bör inte bara adressera de utmaningar som ställs av traditionella centraliserade djupinlärningsmodeller, utan även värna om integriteten, minska kommunikationskostnaderna och övervinna skalbarhetshinder. Federated learning erbjuder en lovande lösning som tillhandahåller en ram för modellträning över decentraliserade noder med fokus på datasekretess. Denna studie analyserar FL Förmåga att förbättra bildklassificering med dess distinkta metoder, jämför dess prestanda med konventionella modeller, och granskar dess vidare implikationer och begränsningar i praktiska, verkliga inställningar. Resultatet av denna studie visar att med lämplig hantering av brus kan FL-modeller uppnå jämförbar noggrannhet med traditionella metoder, där datasekretessen förbättras betydelsefull. Vilket demonstrerar en potential balans mellan prestanda och skydd av integritet i decentraliserade miljöer. / This study aims to explore the effectiveness of Federated Learning (FL) in image classification across decentralized computing environments. With the increasing amount of data generated from mobile and edge computing, particularly image data, there is a need to improve image classification methods that not only address the challenges posed by traditional centralized deep learning models but also respect privacy, reduce communication costs, and overcome scalability barriers. Federated Learning is a promising solution that offers a framework for model training across decentralized nodes with a focus on data privacy. This study analyzes FL's capabilities to enhance image classification using its distinct methodologies, compares its performance with conventional models, and examines its wider implications and limitations in practical, real-world settings. The result of the study indicates that with appropriate noise management, FL models can achieve comparable accuracy to traditional approaches while significantly enhancing data privacy. which demonstrates a potential balance between performance and privacy protection in decentralized environments.

Federated approach for the distributed simulation of a network, is an alternative method that aims to combine existing simulation models and software together using a Run Time Infrastructure (RTI), rather than building the whole simulation from scratch. In this study, an approach that significantly reduces the inter-federate communication load in federated simulation of communication networks is proposed. Rather than communicating packet-level information among federates, characteristics of packet flows in individual federates are dynamically identified and communicated. Flow characterization is done with the Gaussian Mixtures Algorithm (GMA) using a Self Organizing Mixture Network (SOMN) technique. In simulations of a network partitioned into eight federates in space parallel manner, it is shown that significant speedups are achieved with the proposed approach without unduly compromising accuracy.

Cloud computing brought flexibility, scalability, and capital cost savings to the IT industry. As more companies turn to cloud solutions, securing cloud based services becomes increasingly important, because for many organizations, the final barrier to adopting cloud computing is whether it is sufficiently secure. More users rely on cloud storage as it is mainly because cloud storage is available to be used by multiple devices (e.g. smart phones, tablets, notebooks, etc.) at the same time. These services often offer adequate protection to user's private data. However, there were cases where user's private data was accessible to other users, since this data is stored in a multi-tenant environment. These incidents reduce the trust of cloud storage service providers, hence there is a need to securely migrate data from one cloud storage provider to another. This thesis proposes a design of a service for providing Security as a Service for cloud brokers in a federated cloud. This scheme allows customers to securely migrate from one provider to another. To enable the design of this scheme, possible security and privacy risks of a cloud storage service were analysed and identified. Moreover, in order to successfully protect private data, data protection requirements (for data retention, sanitization, and processing) were analysed. The proposed service scheme utilizes various encryption techniques and also includes identity and key management mechanisms, such as "federated identity management". While our proposed design meets most of the defined security and privacy requirements, it is still unknown how to properly handle data sanitization, to meet data protection requirements, and provide users data recovery capabilities (backups, versioning, etc.). / Cloud computing erbjuder flexibilitet, skalbarhet, och kapital kostnadsbesparingar till IT-industrin. Eftersom fler företag vänder sig till moln lösningar, trygga molntjänster blir allt viktigare, eftersom det för många organisationer, det slutliga hindret att anta cloud computing är om det är tillräckligt säkert. Fler användare förlita sig påmoln lagring som det är främst pågrund moln lagring är tillgängligt att användas av flera enheter (t.ex. smarta telefoner, tabletter, bärbara datorer, etc.) påsamtidigt. Dessa tjänster erbjuder ofta tillräckligt skydd för användarens privata data. Men det fanns fall där användarens privata uppgifter var tillgängliga för andra användare, eftersom denna data lagras i en flera hyresgäster miljö. Dessa händelser minskar förtroende molnleverantörer lagring tjänsteleverantörer, därför finns det ett behov av att säkert migrera data från en moln lagring till en annan. Denna avhandling föreslår en utformning av en tjänst för att erbjuda säkerhet som tjänst för molnmäklare i en federativ moln. Detta system gör det möjligt för kunderna att säkert flytta från en leverantör till en annan. För att möjliggöra utformningen av detta system, möjliga säkerhet och risker integritet av ett moln lagring tjänst har analyserats och identifierats. Dessutom att man framgångsrikt skydda privata uppgifter, dataskydd krav (för data retention, sanering och bearbetning) analyserades. Den föreslagna tjänsten systemet utnyttjar olika krypteringsteknik och även inkluderar identitet och nyckelhantering mekanismer, såsom "federerad identitetshantering". Även om vår föreslagna utformningen uppfyller de flesta av den definierade säkerhet och integritet krav, är det fortfarande okänt hur korrekt hantera data sanering, för att uppfyller kraven för dataskydd och ge användarna data recovery kapacitet (säkerhetskopior, versionshantering osv.)