Federated Learning (FL) has emerged as a promising paradigm that addresses the delicate balance between data-intensive model development and the preservation of user privacy. Unlike the conventional approach of aggregating large volumes of raw data in a single data center, FL conducts local training on various devices or institutional serversâsometimes referred to as âclientsââand only exchanges model parameters or gradients with a central entity. By design, this decentralized framework keeps personal or proprietary data within the confines of the originating device or organization, significantly reducing the chances of exposing sensitive information. A primary motivation for FL is the ever-increasing concern over privacy violations and compliance with stringent regulations such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA). As global data protection standards continue to evolve, FL offers a compelling solution by minimizing direct data sharing and thereby mitigating the risk of large-scale breaches. Beyond privacy considerations, FL holds practical appeal in many real-world scenarios, including healthcare, finance, the Internet of Things (IoT), and various consumer-focused applications. These sectors routinely handle confidential or regulated dataâmedical records, bank transactions, or user habitsâwhere a centralized data repository poses both security and compliance hazards. Nevertheless, FL also introduces its own set of challenges. Heterogeneous data distributions across clients can lead to biases and uneven training dynamics. Additionally, new threat vectorsâsuch as model poisoning and inference attacksâhave surfaced within decentralized training environments, prompting research into robust security strategies. Furthermore, practical implementation demands careful planning around communication overhead, computational capacity of clients, and the trade-offs that arise when adding privacy guarantees like Differential Privacy or Secure Multi-Party Computation. This paper explores the theoretical underpinnings of Federated Learning, reviews cutting-edge privacy-preserving techniques, examines potential security pitfalls, and presents real-world applications augmented by case studies. We also discuss performance evaluation methods crucial for determining FLâs viability and highlight upcoming research directions that can shape a secure, efficient, and privacy-centered AI ecosystem.
The correctness of a computation can be efficiently verified in a privacy-preserving manner without re-execution using zero-knowledge succinct non-interactive arguments of knowledge (zkSNARKs). With short transcript sizes and fast verification times, zkSNARKs enable the potential deployment of computationally intensive algorithmsâsuch as machine learning modelsâon the blockchain, making them efficiently verifiable through short proofs. However, the prover time for matrix computations in these settings often fails to scale efficiently with increasing model complexity and data size. We are the first to systematically address zkSNARKs for general matrix computations with practical prover efficiency. We achieve an $O(N + nM)$ prover time, asymptotically faster than the unverified matrix computation, for computations involving $M$ matrix operations on $n \times n$ matrices with $N$ total non-zero entries. Starting with a single dense matrix multiplication, we propose zkMatrix, a special-purpose zkSNARK for verifying committed $n \times n$ matrix multiplication through their projections onto random vectors. Among zkSNARKs with $O(\log n)$ transcript size and verifier time, zkMatrix is the first to achieve $O(n^2)$ prover time and $O(n^2)$ RAM usage. Batching multiple proofs together reduces the prover time for each additional multiplication to $O(n)$ group operations. Next, we design zkSNARKs for sparse matrix multiplication with $N$ non-zero entries. zkSmart reduces the prover time from $O(n^2)$ to $O(N + n)$, relying on an $O(N + n)$-prover vector-matrix-vector product argument, achieved by improving Bulletproofs. Moreover, \zksmart formulates verifiable computation represented as a matrix circuit of $M$ nodes, each denoting a matrix operation. Sparse matrix multiplication translates the matrix circuit satisfiability (Mat-Circ-SAT) problem into the high-dimensional rank-1 constraint system (HD-R1CS), a matrix-circuit version of the rank-1 constraint system (R1CS), traditionally used for arithmetic circuits. Using zkSmart, we achieve $O(N + nM)$ prover time for general matrix computations. To reduce the cost of committing to intermediate variable matrices in zkSmart, we introduce Evalyn, which generates proofs using a pre-order tree traversal on the abstract syntax tree (AST) of a matrix expression. Evalyn ensures output and input consistency in serial matrix computations by linking randomness for zkSNARKs between parent and child nodes, eliminating the need to commit to the nodes and significantly improving prover efficiency. Our prover for R1CS outperforms state-of-the-art general-purpose zkSNARKs. As a foundational component of our framework, we optimize Bulletproofs to construct the fastest known inner product argument (IPA). Additionally, we propose a zero-knowledge transformation that commits to transcript elements with only logarithmic overheadâwhile maintaining compatibility with post-quantum secure, non-homomorphic commitment schemes. We apply our framework to zero-knowledge machine learning (zkML), providing zkSNARKs for neural networks. We translate floating-point truncations and non-linear activation functions into linear algebra equations that can be verified by our framework. We utilize our framework to generate efficient proofs for the attention layer in large language models (LLMs). After resolving all these challenges, we have thoroughly addressed the design of efficient zkSNARKs for matrix computations.
The rapid advancement of technology and the widespread adoption of various IoT devices have resulted in significant challenges in handling and analyzing the vast and diverse volumes of data they produce. Conventional machine learning methodologies, which require data aggregation in a centralized repository for analysis, are often unfeasible due to the significant data volume, limited communication bandwidth, and strict security and privacy requirements. Federated Learning (FL) presents an innovative resolution by facilitating data analysis to take place directly at the data origin, federating the outcomes to generate results comparable to centralized processing. Due to the advancements in growth of federated learning architecture, a number of open-source frameworks have been established to implement this strategy. These frameworks facilitate a range of applications, including healthcare and finance, as well as IoT and smart city initiatives, by enabling data to remain decentralized while still supporting the development of comprehensive analytical models. This study provides a comprehensive evaluation of these established open-source FL frameworks, examining their applicability across various sectors and highlighting their advantages and limitations. The authors examine the various architectural structures, supported algorithms, level of implementation ease, and community support of each framework. The assessment additionally takes into account the scalability of these frameworks and their flexibility in various data scenarios. Through the assessment of the current capabilities and developmental phases of these FL frameworks, this study aims to support practitioners and researchers in identifying the most suitable tools for their specific needs. This analysis highlights the significance of FL in facilitating secure and effective data analysis in the contemporary technological landscape.
Farhana Javed, Josep ManguesâBafalluy, Engin Zeydan, Luis Blanco
This paper proposes a blockchain-enabled framework to enhance trust, transparency, and collaboration in Open Radio Access Network (O-RAN) infrastructures through Federated Learning (FL). Traditional O-RAN architectures and centralized machine learning approaches face challenges when integrating multi-vendor environments, primarily due to lack of trust, proprietary data concerns, and limited interoperability. Our solution transitions from implicit trust, where the reliability of contributions is assumed, to explicit trust, where reputation is verifiably established on-chain. We introduce a blockchain-based reputation mechanism that evaluates the accuracy, integrity, and quality of participantsâ model updates within the FL process. Smart contracts automate critical tasks-such as participant registration, model update verification, and reputation scoring-ensuring that data inputs directly influence accountability in a tamper-proof, transparent manner. By deploying the framework on a scalable Layer 2 blockchain (Polygon) testnet and proposing the use of a blockchain oracle within this architectural framework for secure off-chain computations, this work focuses on a conceptual architectural approach by aligning with O-RANâs architecture to propose and deploy a Decentralized Application (DApp) on the blockchain. The proposed framework emphasizes a conceptual design over performance optimization and is structured to naturally benefit from ongoing improvements in blockchain scalability, which may reduce latency and enhance operational efficiency over time. Smart contracts for crucial processes and reputation calculation are included within our proposed DApp. The implementation of this work is publicly accessiblehttps://github.com/farhanajaved/Reputation_O-RAN.
Xin Wang, Li Jiaqian, Ding Xueshuang, H. Zhang ¡ 5 authors
The problem of data privacy protection in the information age deserves peopleâs attention. As a distributed machine learning technology, federated learning can effectively solve the problem of privacy security and data silos. Differential privacy(DP) technology is applied in federated learning(FL). By adding noise to raw data and model parameters, it can further enhance the degree of data privacy protection. Over the years, differential privacy technology based on federated learning framework has been developed, which is divided into central differential privacy federated learning(CDPFL) and local differential privacy federated learning(LDPFL). Although differential privacy may reduce the accuracy and convergence of federated learning models while protecting data privacy, researchers have proposed a variety of optimization methods to balance privacy protection and model performance. This paper comprehensively expounds the research status of differential privacy techniques based on the federated learning framework, first providing detailed introductions to federated learning and differential privacy technologies, and then summarizing the development status of two types of federated learning differential privacy(DPFL) techniques respectively; for CDPFL, the paper divides the discussion into first proposal of CDP and typical application examples, the impact of Gaussian mechanisms on model accuracy, optimization based on asynchronous differential privacy, and insights from other scholars; for LDPFL, the paper divides the discussion into first proposal of LDP and typical application examples, processing multidimensional data and improving model accuracy, existing methods and optimization for reducing communication costs, balancing privacy protection and data usability, LDPFL based on the Shuffle model, and insights from other scholars; following this, the paper addresses and summarizes the unique challenges introduced by incorporating differential privacy into federated learning and proposes solutions; finally, based on a summary of existing optimization techniques, the paper outlines future directions and specifically discusses three research ideas for enhancing the optimization effects of federated differential privacy: advanced optimization strategies combining Bayesian methods and the Alternating Direction Method of Multipliers (ADMM), integrating lattice homomorphic encryption techniques from cryptography to achieve more efficient differential privacy protection in federated learning, and exploring the application of zero-knowledge proof techniques in federated learning for privacy protection.
Jianping Yu, Hang Yao, Kai Ouyang, Xiaojun Cao ¡ 5 authors
Federated Learning (FL) enables clients to securely share gradients computed on their local data with the server, thereby eliminating the necessity to directly expose their sensitive local datasets. In traditional FL, the server might take advantage of its dominant position during the model aggregation process to infer sensitive information from the shared gradients of the clients. At the same time, malicious clients may submit forged and malicious gradients during model training. Such behavior not only compromises the integrity of the global model, but also diminishes the usability and reliability of trained models. To effectively address such privacy and security attack issues, this work proposes a Blockchain-based Privacy-preserving and Secure Federated Learning (BPS-FL) scheme, which employs the threshold homomorphic encryption to protect the local gradients of clients. To resist malicious gradient attacks, we design a Byzantine-robust aggregation protocol for BPS-FL to realize the cipher-text level secure model aggregation. Moreover, we use a blockchain as the underlying distributed architecture to record all learning processes, which ensures the immutability and traceability of the data. Our extensive security analysis and numerical evaluation demonstrate that BPS-FL satisfies the privacy requirements and can effectively defend against poisoning attacks.
Decentralized Federated Learning improves data privacy and eliminates single points of failure by removing reliance on centralized storage and model aggregation in distributed computing systems. Ensuring the integrity of computations during local model training is a significant challenge, especially before sharing gradient updates from each local client. Current methods for ensuring computation integrity often involve patching local models to implement cryptographic techniques, such as Zero-Knowledge Proofs. However, this approach becomes highly complex and sometimes impractical for large-scale models that use techniques such as random dropouts to improve training convergence. These random dropouts create non-deterministic behavior, making it challenging to verify model updates under deterministic protocols. We propose ProxyZKP, a novel framework combining Zero-Knowledge Proofs with polynomial proxy models to provide computation integrity in local training to address this issue. Each local node combines a private model for online deep learning applications and a proxy model that mediates decentralized model training by exchanging gradient updates. The multivariate polynomial nature of proxy models facilitates the application of Zero-Knowledge Proofs. These proofs verify the computation integrity of updates from each node without disclosing private data. Experimental results indicate that ProxyZKP significantly reduces computational load. Specifically, ProxyZKP achieves proof generation times that are 30-50% faster compared to established methods like zk-SNARKs and Bulletproofs. This improvement is largely due to the high parallelization potential of the univariate polynomial decomposition approach. Additionally, integrating Differential Privacy into the ProxyZKP framework reduces the risk of Gradient Inversion attacks by adding calibrated noise to the gradients, while maintaining competitive model accuracy. The results demonstrate that ProxyZKP is a scalable and efficient solution for ensuring training integrity in decentralized federated learning environments, particularly in scenarios with frequent model updates and the need for strong model scalability.
Leveraging blockchain in Federated Learning (FL) emerges as a new paradigm for secure collaborative learning on Massive Edge Networks (MENs). As the scale of MENs increases, it becomes more difficult to implement and manage a blockchain among edge devices due to complex communication topologies, heterogeneous computation capabilities, and limited storage capacities. Moreover, the lack of a standard metric for blockchain security becomes a significant issue. To address these challenges, we propose a lightweight blockchain for verifiable and scalable FL, namely LiteChain, to provide efficient and secure services in MENs. Specifically, we develop a distributed clustering algorithm to reorganize MENs into a two-level structure to improve communication and computing efficiency under security requirements. Moreover, we introduce a Comprehensive Byzantine Fault Tolerance (CBFT) consensus mechanism and a secure update mechanism to ensure the security of model transactions through LiteChain. Our experiments based on Hyperledger Fabric demonstrate that LiteChain presents the lowest end-to-end latency and on-chain storage overheads across various network scales, outperforming the other two benchmarks. In addition, LiteChain exhibits a high level of robustness against replay and data poisoning attacks.
Chenhao Ying, Fuyuan Xia, David S. L. Wei, Xinchun Yu ¡ 11 authors
Harnessing the benefits of blockchain, such as decentralization, immutability, and transparency, to bolster the credibility and security attributes of federated learning (FL) has garnered increasing attention. However, blockchain-enabled FL (BFL) still faces several challenges. The primary and most significant issue arises from its essential but slow validation procedure, which selects high-quality local models by recruiting distributed validators. The second issue stems from its incentive mechanism under the transparent nature of blockchain, increasing the risk of privacy breaches regarding workersâ cost information. The final challenge involves data eavesdropping from shared local models. To address these significant obstacles, this paper proposes a Blockchain-enabled Incentivized and Secure Federated Learning (BIT-FL) framework. BIT-FL leverages a novel loop-based sharded consensus algorithm to accelerate the validation procedure, ensuring the same security as non-sharded consensus protocols. It consistently outputs the correct local model selection when the fraction of adversaries among validators is less than$1/2$with synchronous communication. Furthermore, BIT-FL integrates a randomized incentive procedure, attracting more participants while guaranteeing the privacy of their cost information through meticulous worker selection probability design. Finally, by adding artificial Gaussian noise to local models, it ensures the privacy of trainersâ local models. With the careful design of Gaussian noise, the excess empirical risk of BIT-FL is upper-bounded by$\mathcal {O}(\frac{\ln n_{\min}}{ n_{\min}^{3/2}}+\frac{\ln n}{n})$, where$n$represents the size of the union dataset, and$n_{{\min}}$represents the size of the smallest dataset. Our extensive experiments demonstrate that BIT-FL exhibits efficiency, robustness, and high accuracy for both classification and regression tasks.
In recent years, the confluence of federated learning and model parallelism has revolutionized the landscape of deep learning on distributed systems, significantly enhancing efficiency and scalability. Federated learning, a decentralized approach, enables multiple edge devices to collaboratively train a model without sharing their data, thereby preserving privacy and reducing latency. Model parallelism, on the other hand, divides a large model across several devices, allowing for simultaneous computation and faster processing. By synergizing these two paradigms, researchers have developed innovative frameworks that leverage the strengths of both approaches, achieving superior performance and resource utilization. This hybrid strategy addresses the limitations of traditional centralized training, offering a robust solution for large-scale, privacy-sensitive applications.The integration of federated learning and model parallelism not only optimizes computational resources but also mitigates communication bottlenecks inherent in distributed systems. This amalgamation is particularly advantageous for deep learning tasks involving vast datasets and complex models, as it distributes the computational load and enhances fault tolerance. Moreover, this approach supports continuous learning from distributed data sources, facilitating real-time updates and adaptability. As a result, turbocharged AI systems leveraging these technologies can efficiently handle the growing demands of contemporary deep learning applications, paving the way for advancements in fields such as healthcare, finance, and autonomous systems.
Federated Learning (FL) has become a transformative approach in machine learning, allowing decentralized training of models across multiple devices while preserving data privacy. This paradigm addresses critical concerns related to data privacy, security, and communication overhead, making it particularly relevant for applications in domains such as healthcare, finance, and the Internet of Things (IoT). Resource-constrained FL extends this concept to environments where computational, communication, and energy resources are limited, such as edge networks and IoT devices. This extension focuses on optimizing various aspects of the learning process to enable effective model training even in resource-limited settings. The primary aim of this survey is to provide a comprehensive and structured overview of the current state of research in FL and resource-constrained FL. By examining 62 key publications, this survey synthesizes insights and developments across these domains, highlighting advancements, challenges, and gaps that exist. This survey aims to provide a holistic view of the advancements and ongoing challenges in FL and resource-constrained FL. It identifies research gaps and proposes future directions, such as improving communication efficiency, developing adaptive learning algorithms, and enhancing resource management strategies. This survey serves as a valuable resource for researchers, practitioners, and stakeholders in the field, offering practical insights and guiding future exploration and innovation in FL and its applications in resource-constrained environments.
Rongping Lin, Fan Wang, Shan Luo, Xiong Wang ¡ 5 authors
Federated Learning (FL) is a distributed machine learning method that ensures the privacy and security of participantsâ data by avoiding direct data upload to a central node for training. However, the traditional FL typically applies a star structure with cloud servers as the central aggregator for the model parameters from different terminals, leading to problems such as central failure, malicious tampering and malicious participants, resulting in training errors or system crashes. To address these issues, a permissioned blockchain is used to build a secure and reliable data-sharing platform among participating terminals, replacing the central aggregator in the traditional FL called blockchain-based federated learning. However, the block generation method of the blockchain system may introduce significant latency in the federated learning where distributed model parameters upload randomly, resulting in low efficiency of the federated learning. To overcome this, we propose a block generation strategy that groups terminals and generates a block for each group, which minimizes the latency of a single round of federated learning, and an optimal block generation algorithm that considers data distribution, terminal resources, and network resources is provided. The analysis shows that the proposed algorithm can effectively obtain the optimal solution of block generation to minimize the authentication time, and we conduct extensive experiments that demonstrate the time efficiency of the proposed algorithm.
Rafael Marin Machado de Souza, A. I. S. Holm, MĂĄrcio Biczyk, Leandro Nunes de Castro
Federated learning (FL) and bioinspired computing (BIC), two distinct, yet complementary fields, have gained significant attention in the machine learning community due to their unique characteristics. FL enables decentralized machine learning by allowing models to be trained on data residing across multiple devices or servers without exchanging raw data, thus enhancing privacy and reducing communication overhead. Conversely, BIC draws inspiration from nature to develop robust and adaptive computational solutions for complex problems. This paper explores the state of the art in the integration of FL and BIC, introducing BIC techniques and discussing the motivations for their integration with FL. The convergence of these fields can lead to improved model accuracy, enhanced privacy, energy efficiency, and reduced communication overhead. This synergy addresses inherent challenges in FL, such as data heterogeneity and limited computational resources, and opens up new avenues for developing more efficient and autonomous learning systems. The integration of FL and BIC holds promise for various application domains, including healthcare, finance, and smart cities, where privacy-preserving and efficient computation is paramount. This survey provides a systematic review of the current research landscape, identifies key challenges and opportunities, and suggests future directions for the successful integration of FL and BIC.
Chenfei Nie, Yannan Li, Yuxin Yang, Yuede Ji ¡ 5 authors
Federated learning (FL) is an emerging distributed learning paradigm without sharing participating clients' private data. However, existing works show that FL is vulnerable to both Byzantine (security) attacks and data reconstruction (privacy) attacks. Almost all the existing FL defenses only address one of the two attacks. A few defenses address the two attacks, but they are not efficient and effective enough. We propose BPFL, an efficient Byzantine-robust and provably privacy-preserving FL method that addresses all the issues. Specifically, we draw on state-of-the-art Byzantine-robust FL methods and use similarity metrics to measure the robustness of each participating client in FL. The validity of clients are formulated as circuit constraints on similarity metrics and verified via a zero-knowledge proof. Moreover, the client models are masked by a shared random vector, which is generated based on homomorphic encryption. In doing so, the server receives the masked client models rather than the true ones, which are proven to be private. BPFL is also efficient due to the usage of non-interactive zero-knowledge proof. Experimental results on various datasets show that our BPFL is efficient, Byzantine-robust, and privacy-preserving.
Linh Tran, Sanjay Chari, Md. Saikat Islam Khan, Aaron Zachariah ¡ 6 authors
We present the Differentially Private Blockchain-Based Vertical Federal Learning (DP-BBVFL) algorithm that provides verifiability and privacy guarantees for decentralized applications. DP-BBVFL uses a smart contract to aggregate the feature representations, i.e., the embeddings, from clients transparently. We apply local differential privacy to provide privacy for embeddings stored on a blockchain, hence protecting the original data. We provide the first prototype application of differential privacy with blockchain for vertical federated learning. Our experiments with medical data show that DP-BBVFL achieves high accuracy with a tradeoff in training time due to on-chain aggregation. This innovative fusion of differential privacy and blockchain technology in DP-BBVFL could herald a new era of collaborative and trustworthy machine learning applications across several decentralized application domains.
This project focuses on Zero-Knowledge Proofs (ZKPs), a groundbreaking cryptographic technique reshaping data authentication while preserving maximum confidentiality.ZKPs enable the verification of truthfulness in statements without disclosing associated data, ensuring the utmost protection of sensitive information.With applications spanning various domains, including secure authentication protocols, privacy-preserving transactions in decentralized systems like blockchain, and confidential data verification across digital interactions, ZKPs offer versatile solutions for secure communications.The project aims to safeguard sensitive business information during outsourcing service processes.The implementation of ZKPs intends to establish a secure communication framework that fosters trust among stakeholders without compromising sensitive details, ensuring enhanced confidentiality in outsourced operations.At its core, ZKPs empower a prover to convince a verifier of a statement's validity without revealing underlying data, establishing an unmatched level of security and privacy.This concept shields against unauthorized access and data breaches, fostering trust between entities without the exchange of sensitive details.The versatility of ZKPs extends beyond authentication, influencing secure voting systems, safeguarding digital identities, and facilitating confidential transactions while upholding user privacy.
Chaehyeon Lee, Jonathan Heiss, Stefan Tai, James WonâKi Hong
Verifiable decentralized federated learning (FL) systems combining blockchains and zero-knowledge proofs (ZKP) make the computational integrity of local learning and global aggregation verifiable across workers. However, they are not end-to-end: data can still be corrupted prior to the learning. In this paper, we propose a verifiable decentralized FL system for end-to-end integrity and authenticity of data and computation extending verifiability to the data source. Addressing an inherent conflict of confidentiality and transparency, we introduce a two-step proving and verification (2PV) method that we apply to central system procedures: a registration workflow that enables non-disclosing verification of device certificates and a learning workflow that extends existing blockchain and ZKP-based FL systems through non-disclosing data authenticity proofs. Our evaluation on a prototypical implementation demonstrates the technical feasibility with only marginal overheads to state-of-the-art solutions.
Secure aggregation enables federated learning (FL) to perform collaborative training of clients from local gradient updates without exposing raw data. However, existing secure aggregation schemes inevitably perform an expensive fresh setup per round because each client needs to establish fresh input-independent secrets over different rounds. The latest research, Flamingo (S&P 2023), designed a share-transfer-based reusable secret key to support the server continuously performing multiple rounds of aggregation. Nevertheless, the share transfer mechanism it proposed can only be achieved with P probability, which has limited reliability. To tackle the aforementioned problems, we propose a more reliable and anonymously authenticated scheme called Chu-ko-nu for multi-round secure aggregation. Specifically, in terms of share transfer, Chu-ko-nu breaks the probability P barrier by supplementing a redistribution process of secret key components (the sum of all components is the secret key), thus ensuring the reusability of the secret key. Based on this reusable secret key, Chu-ko-nu can efficiently perform consecutive aggregation in the following rounds. Furthermore, considering the client identity authentication and privacy protection issue most approaches ignore, Chu-ko-nu introduces a zero-knowledge proof-based authentication mechanism. It can support clients anonymously participating in FL training and enables the server to authenticate clients effectively in the presence of various attacks. Rigorous security proofs and extensive experiments demonstrated that Chu-ko-nu can provide reliable and anonymously authenticated aggregation for FL with low aggregation costs, at least a 21.02% reduction compared to the state-of-the-art schemes.
Distributed machine learning, and Decentralized Federated Learning in particular, is emerging as an effective solution to cope with the ever-increasing amount of data and the need to process it faster and more reliably. It enables machine learning models to be trained without centralizing user data, which improves data confidentiality and optimizes performance compared with centralized approaches. However, scaling up such systems can have limitations in terms of data and model traceability and security. To address this limitation, the integration of Blockchain has been proposed, forming a global system leveraging Blockchain, called Blockchain Based Decentralized Federated Learning (BDFL), and taking advantage of the benefits of this technology, namely transparency, immutability and decentralization. For the time being, few studies have sought to characterize these BDFL systems, although it seems that they can be broken down into a set of layers (blockchain, interconnection of DFL nodes, client selection, data transmission, consensus management) that could have a major impact on the operation of the BDFL as a whole. The aim of this article is therefore to respond to this limitation by highlighting the different layers existing in the architecture of a BDFL system and the solutions proposed in the literature that can be integrated to optimise both the performance and the security of the system. This could ultimately lead to the design of more secure and efficient architectures with greater resilience to attacks and architectural changes.
Federated Learning (FL) has emerged as a revolutionary machine learning approach, enabling the training of algorithms across decentralized devices or servers while maintaining data privacy. Unlike traditional centralized methods that pool data into a single repository, FL keeps data localized, enhancing the protection of sensitive information and ensuring compliance with privacy standards like GDPR and CCPA. This paradigm shift is particularly relevant in today's data-driven world, where concerns over data breaches and regulatory compliance are paramount. FL allows organizations and individuals to collaboratively train powerful machine learning models without sharing sensitive data. By adopting FL approaches, leveraging distributed data and computing power across different sources while respecting user privacy becomes possible. The architecture of FL involves a central system coordinating updates from multiple sources to improve a global model. Edge devices, such as smartphones or IoT devices, perform local training using their unique datasets. Each edge device trains the model locally, sending only updates (like gradients) to the central server, ensuring sensitive data is never exposed1. Furthermore, privacy-preserving technologies like differential privacy and homomorphic encryption strengthen data confidentiality and compliance with regulations. Differential privacy introduces noise to data or model updates to prevent the reconstruction of individual information, while homomorphic encryption allows computations on encrypted data without decryption1. The rise of 5G networks will significantly enhance FL by reducing latency and improving communication between edge devices and central servers, enabling faster model training and real-time applications. Blockchain technology offers a decentralized and immutable ledger for tracking data usage and model updates, creating a transparent and tamper-proof mechanism, addressing trust issues in federated systems and further strengthening security
Interest in supporting Federated Learning (FL) using blockchains has grown significantly in recent years. However, restricting access to the trained models only to actively participating nodes remains a challenge even today. To address this concern, we propose a methodology that incentivizes model parameter sharing in an FL setup under Local Differential Privacy (LDP). The nodes that share less obfuscated data under LDP are awarded higher quantum of tokens, which they can later use to obtain session keys for accessing encrypted model parameters updated by the server. If one or more of the nodes do not contribute to the learning process by sharing their data, or share only highly perturbed data, they earn less number of tokens. As a result, such nodes may not be able to read the new global model parameters if required. Local parameter sharing and updating of global parameters are done using the distributed ledger of a permissioned blockchain, namely HyperLedger Fabric (HLF). Being a blockchain-based approach, the risk of a single point of failure is also mitigated. Appropriate chaincodes, which are smart contracts in the HLF framework, have been developed for implementing the proposed methodology. Results of an extensive set of experiments firmly establish the feasibility of our approach.
Privacy and trust are highly demanding in practical recommendation engines. Although Federated Learning (FL) has significantly addressed privacy concerns, commercial operators are still worried about several technical challenges while bringing FL into production. In addition, classical FL has several intrinsic operational limitations such as single-point failure, data and model tampering, and heterogenic clients participating in the FL process. To address these challenges in practical recommenders, we propose a responsible recommendation generation framework based on blockchain-empowered asynchronous FL that can be adopted for any model-based recommender system. In standard FL settings, we build an additional aggregation layer in which multiple trusted nodes guided by a mediator component perform gradient aggregation to achieve an optimal model locally in a parallel fashion. The mediator partitions users into K clusters, and each cluster is represented by a cluster head. Once a cluster gets semi-global convergence, the cluster head transmits model gradients to the FL server for global aggregation. In addition the trusted cluster heads are responsible to submit the converged semi-global model to a blockchain to ensure tamper resilience. In our settings, an additional mediator component works like an independent observer that monitors the performance of each cluster head, updates a reward score, and records it into a digital ledger. Finally, evaluation results on three diversified benchmarks illustrate that the recommendation performance on selected measures is considerably comparable with the standard and federated version of a well-known neural collaborative filtering recommender.
Federated learning, as one of the three main technical routes for privacy computing, has been widely studied and applied in both academia and industry. However, malicious nodes may tamper with the algorithm execution process or submit false learning results, which directly affects the performance of federated learning. In addition, learning nodes can easily obtain the global model. In practical applications, we would like to obtain the federated learning results only by the demand side. Unfortunately, no discussion on protecting the privacy of the global model is found in the existing research. As emerging cryptographic tools, the zero-knowledge virtual machine (ZKVM) and homomorphic encryption provide new ideas for the design of federated learning frameworks. We have introduced ZKVM for the first time, creating learning nodes as local computing provers. This provides execution integrity proofs for multi-class machine learning algorithms. Meanwhile, we discuss how to generate verifiable proofs for large-scale machine learning tasks under resource constraints. In addition, we implement the fully homomorphic encryption (FHE) scheme in ZKVM. We encrypt the model weights so that the federated learning nodes always collaborate in the ciphertext space. The real results can be obtained only after the demand side decrypts them using the private key. The innovativeness of this paper is demonstrated in the following aspects: 1. We introduce the ZKVM for the first time, which achieves zero-knowledge proofs (ZKP) for machine learning tasks with multiple classes and arbitrary scales. 2. We encrypt the global model, which protects the model privacy during local computation and transmission. 3. We propose and implement a new federated learning framework. We measure the verification costs under different federated learning rounds on the IRIS dataset. Despite the impact of homomorphic encryption on computational accuracy, the framework proposed in this paper achieves a satisfactory 90% model accuracy. Our framework is highly secure and is expected to further improve the overall efficiency as cryptographic tools continue to evolve.