This paper presents a novel approach to distributed learning leveraging Federated Bayesian Networks (FBNs). Traditional federated learning methods struggle with capturing complex, non-independent data distributions, often leading to suboptimal global models. We introduce a framework where multiple devices collaboratively learn a Bayesian Network model through decentralized updates, explicitly addressing these dependency challenges. The core idea is to allow devices to share probabilistic models and inference results, creating a system that adapts to local data characteristics while maintaining data privacy. The framework incorporates techniques for managing network topology, handling heterogeneous data distributions, and ensuring convergence of the collaborative learning process. We demonstrate the potential of this approach through a theoretical analysis and outline key considerations for practical implementation, highlighting its advantages over conventional federated learning systems. The primary contribution lies in the systematic application of Bayesian Networks to federated learning, providing a robust mechanism for learning from correlated data sources.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper presents a novel approach to distributed machine learning, termed Federated Learning with Differential Privacy (FLDP), which addresses the critical challenge of privacy preservation in collaborative model training. Traditional federated learning techniques, while mitigating the risks associated with centralized data collection, still expose model updates, potentially revealing sensitive information about the underlying data. FLDP overcomes this limitation by directly applying differential privacy to the model aggregation process. Specifically, we introduce a locally sensitive differential privacy mechanism that injects noise into each node's model update before aggregation. This ensures that the impact of any single node's contribution on the global model is bounded, effectively protecting individual data privacy. The proposed method allows for reliable model convergence while rigorously upholding privacy guarantees. We demonstrate the feasibility and effectiveness of FLDP through a theoretical analysis and outline a practical implementation strategy. The key contribution of this work lies in the shift from applying differential privacy solely to data training to directly incorporating it into the model aggregation phase, creating a more robust and privacy-preserving distributed learning system.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) presents a promising approach to training machine learning models on decentralized data sources while preserving user privacy. However, traditional FL methods often rely on a central server, introducing a single point of failure and potential privacy risks. This paper proposes a novel decentralized federated learning system that leverages threshold cryptography and differential privacy to address these concerns. The core claim is that protecting user privacy in federated learning remains a significant challenge, and this system provides a robust solution. The system operates through a series of distributed rounds where participants collaboratively update model parameters using threshold cryptography to ensure secure aggregation and differential privacy to mitigate individual data exposure. This approach eliminates the need for a central server, enhancing both privacy and security. The system is designed for scalability and adaptability, making it suitable for various decentralized data scenarios. This work contributes to the development of more secure and privacy-preserving federated learning solutions.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper proposes a novel approach to decentralized federated learning (DFL) that leverages secure multi-party computation (SMPC) to guarantee data privacy during collaborative model training. Traditional federated learning methods, while promoting data sharing for model improvement, inherently expose individual datasets to the central server, raising significant privacy concerns. Our framework addresses this limitation by employing SMPC protocols, enabling model updates to be aggregated securely without revealing the underlying data. This approach provides a strong privacy guarantee, combining the benefits of federated learning with robust privacy protection. We present a detailed description of the system architecture, the SMPC protocols utilized, and the mathematical formulation underpinning the aggregation process. The core claim of this work is the ability to enable collaborative model training across multiple parties without revealing individual data. The core mechanism relies on implementing a federated learning framework based on secure multi-party computation protocols, where model updates are aggregated securely without exposing the underlying data. This research represents a significant advancement in the field of privacy-preserving machine learning.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper proposes a novel approach to decentralized federated learning (DFL) that incorporates Byzantine fault tolerance (BFT) using blockchain consensus. Traditional DFL systems are vulnerable to malicious clients injecting poisoned model updates, compromising the overall model accuracy and data integrity. Our system leverages a blockchain network to provide a robust and verifiable mechanism for validating model updates. Each client's update is cryptographically signed and submitted to the blockchain. The blockchain then employs a consensus algorithm to verify the update's validity, ensuring that only legitimate updates are added to the global model. This approach significantly enhances the security and reliability of DFL, particularly in environments with untrusted participants. The core claim is that blockchain-based consensus mechanisms can provide robust BFT for DFL, while the core mechanism involves using a blockchain network to verify and validate model updates. This addresses the security vulnerabilities of traditional DFL by utilizing the inherent properties of blockchain technology. We demonstrate the feasibility and effectiveness of this system through a detailed theoretical analysis and design considerations.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without directly exchanging data. However, the inherent non-IID (independent and identically distributed) nature of data across clients poses a significant threat to the privacy guarantees provided by traditional differential privacy (DP) mechanisms. This paper introduces a novel differential privacy framework specifically designed for federated learning scenarios with non-IID data. Our approach incorporates adaptive noise scaling, dynamically adjusting the privacy budget based on the measured data heterogeneity among clients. This tailored mechanism mitigates the increased privacy risk associated with non-IID data, providing a more robust and effective solution for privacy-preserving federated learning. We demonstrate the effectiveness of our method through theoretical analysis and highlight its advantages over conventional DP techniques in this context.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper proposes a novel framework for distributed causal inference by integrating federated learning with Bayesian networks. Traditional causal inference methods often require centralized data access, posing significant privacy concerns and logistical challenges, particularly in scenarios involving sensitive data distributed across multiple entities. Our approach addresses this limitation by enabling each participating entity to simultaneously learn causal relationships within its local data using Bayesian networks. These locally learned models are then aggregated to construct a global causal model, mitigating the need for centralized data sharing. We introduce a specific federated learning architecture tailored for causal discovery, incorporating techniques to address confounding and selection bias. The core of the method lies in the iterative refinement of Bayesian network structures through distributed learning, followed by weighted averaging of the learned parameters. We demonstrate the potential of this method through a theoretical analysis, outlining its advantages in terms of privacy preservation, scalability, and robustness. The resulting global causal model provides insights into the underlying causal relationships while respecting data locality. This approach offers a viable pathway for causal inference in distributed, privacy-sensitive environments.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) presents a promising approach to training machine learning models on decentralized data sources while preserving user privacy. However, traditional FL methods often rely on a central server, introducing a single point of failure and potential privacy risks. This paper proposes a novel decentralized federated learning system that leverages threshold cryptography and differential privacy to address these concerns. The core claim is that protecting user privacy in federated learning remains a significant challenge, and this system provides a robust solution. The system operates through a series of distributed rounds where participants collaboratively update model parameters using threshold cryptography to ensure secure aggregation and differential privacy to mitigate individual data exposure. This approach eliminates the need for a central server, enhancing both privacy and security. The system is designed for scalability and adaptability, making it suitable for various decentralized data scenarios. This work contributes to the development of more secure and privacy-preserving federated learning solutions.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
The creation and maintenance of digital twins for critical infrastructure systems, such as power grids, water distribution networks, and transportation systems, presents significant computational challenges. Traditional centralized approaches struggle to handle the massive amounts of data generated by distributed sensors and actuators, leading to communication bottlenecks and potential privacy concerns. This paper proposes a novel framework that integrates federated learning and edge computing to overcome these limitations. The framework enables decentralized model training and updates for the digital twin, reducing communication overhead and preserving data privacy. The core mechanism involves data aggregation and processing at the edge, followed by federated learning to iteratively refine the digital twin model. This approach offers a scalable and efficient solution for infrastructure management, enabling real-time monitoring, predictive maintenance, and optimized operational decisions. The key contributions of this work lie in the synergistic combination of these technologies, delivering a robust and adaptable system for managing complex infrastructure.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated Learning (FL) offers a promising approach to training machine learning models on decentralized data while preserving data privacy. However, the inherent heterogeneity of data across clients and potential malicious behavior introduce challenges to the trustworthiness of FL systems. This work proposes a novel information-theoretic framework for quantifying trust in FL, moving away from traditional subjective trust assumptions. We define a "trust score" based on the mutual information between local model updates and a global consensus model. This score directly measures the contribution of each client's update to the collective knowledge, providing a rigorous metric for assessing model divergence and identifying potential outliers. The core contribution of this paper lies in providing a quantifiable and objective method for evaluating trust in FL, enabling more robust and reliable deployments. We explore the theoretical properties of this mutual information-based trust score and demonstrate its potential for improved outlier detection and model convergence in federated learning scenarios. The framework utilizes concepts from information theory, specifically mutual information, to provide a mathematically grounded approach to assessing the quality and trustworthiness of decentralized model training.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper presents a novel approach to differential privacy in federated learning, termed Dynamic Differential Privacy (DDP). The core idea is to adapt the privacy budget dynamically, responding to the varying sensitivity of local data. Traditional federated learning frequently utilizes a static privacy budget, which can lead to either overly conservative privacy protection, significantly impacting model accuracy, or insufficient protection when confronted with malicious adversaries. DDP addresses these limitations by iteratively adjusting the privacy budget (ε, δ) based on gradient variance and update divergence. The algorithm reduces the privacy budget when gradients exhibit high variance, indicating sensitive data, and increases it when a node provides substantially different updates, signaling potential adversarial behavior. We demonstrate that this dynamic adaptation provides a stronger privacy guarantee while maintaining acceptable accuracy levels compared to fixed-budget approaches. This work contributes to a more robust and practical implementation of federated learning in privacy-sensitive environments.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without direct data sharing. However, traditional FL methods are vulnerable to information leakage and model divergence, particularly when dealing with highly heterogeneous client datasets. This research proposes a novel framework that combines differential privacy (DP) with personalized model aggregation (PMA) to mitigate these issues. The core claim is that integrating DP safeguards client data while PMA allows for adaptation of the global model to individual client characteristics. We introduce a rigorous methodology for quantifying the trade-offs between privacy, model accuracy, and computational overhead. The proposed approach enhances both the robustness and effectiveness of FL systems, paving the way for more secure and adaptable distributed learning applications. Specifically, we formulate the aggregation process using the following notation: Let $m_i$ represent the model received from client *i*, $s_i$ be the local data used by client *i*, and $\epsilon$ and $\delta$ be the privacy parameters. The personalized aggregation function is defined as: $m_{aggregated} = \frac{\sum_{i=1}^{K} \alpha_i * m_i}{\sum_{i=1}^{K} \alpha_i}$ where $\alpha_i$ are weights determined based on client data characteristics and privacy constraints. We leverage differential privacy by adding noise to the model updates, represented as: $m_i' = m_i + \epsilon * N(0, I_d)$ where $N(0, I_d)$ denotes Gaussian noise with mean 0 and covariance matrix $I_d$ (d-dimensional identity matrix).
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations