Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources, primarily located at edge devices. However, the inherent distributed nature of FL introduces significant challenges, particularly regarding privacy vulnerabilities and substantial communication overhead. This paper proposes a novel framework for distributed learning with differential privacy tailored for federated edge computing environments. The core idea is to integrate a customized differential privacy mechanism with a hierarchical learning structure and adaptive privacy budgets, all while exploiting hardware-accelerated cryptographic techniques to reduce communication costs. Our approach aims to simultaneously mitigate privacy risks and improve the efficiency of FL deployments across geographically diverse edge devices. We define the following key components: (1) A hierarchical learning structure consisting of local and global layers; (2) A novel differential privacy mechanism utilizing homomorphic encryption and secure multi-party computation; (3) Adaptive privacy budget allocation based on device heterogeneity and data sensitivity. The system is designed to minimize communication, maximize privacy, and improve the overall performance of FL in resource-constrained edge environments. The proposed method provides a theoretical framework for achieving strong privacy guarantees while maintaining reasonable communication costs.
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, this paradigm is increasingly vulnerable to adversarial attacks, where malicious participants can manipulate the training process to infer sensitive information about individual users. This paper proposes a novel framework combining adversarial training with differential privacy to mitigate these security risks. Our approach trains models robust against attacks aimed at extracting private data while simultaneously guaranteeing differential privacy for each participant. We introduce a modified training loop incorporating adversarial loss alongside the standard FL loss, and demonstrate its effectiveness through theoretical analysis and a conceptual examination. The key contribution lies in the synergistic combination of these two techniques, creating a more secure and privacy-preserving federated learning system. The goal is to provide a foundational approach for building robust FL systems.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources, preserving data privacy. However, the inherent data heterogeneity across clients introduces a significant challenge: algorithmic bias. This paper presents a novel method for detecting and quantifying bias within the federated learning process. Our approach leverages statistical measures and differential privacy techniques to monitor model updates and identify bias amplification. We define key metrics such as variance of model updates, divergence between client models, and the sensitivity of model predictions to sensitive attributes. The core of our method is the adaptive adjustment of learning rates based on these metrics, aiming to mitigate bias while maintaining model convergence. We demonstrate the effectiveness of our approach through a theoretical analysis and a conceptual framework, highlighting its potential for robust and fair FL systems. The proposed framework provides a quantifiable assessment of bias risk and suggests strategies for bias mitigation during the training process.
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, this paradigm is increasingly vulnerable to adversarial attacks, where malicious participants can manipulate the training process to infer sensitive information about individual users. This paper proposes a novel framework combining adversarial training with differential privacy to mitigate these security risks. Our approach trains models robust against attacks aimed at extracting private data while simultaneously guaranteeing differential privacy for each participant. We introduce a modified training loop incorporating adversarial loss alongside the standard FL loss, and demonstrate its effectiveness through theoretical analysis and a conceptual examination. The key contribution lies in the synergistic combination of these two techniques, creating a more secure and privacy-preserving federated learning system. The goal is to provide a foundational approach for building robust FL systems.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) presents a promising paradigm for training machine learning models on decentralized data sources without directly exchanging the data itself. However, achieving differential privacy (DP) – a rigorous privacy guarantee – within the FL setting remains a significant challenge due to the computational overhead associated with traditional DP mechanisms. This work introduces a novel approach that combines differential privacy with secure multi-party computation (SMPC) to address this limitation. Our method employs a layered SMPC protocol to enable clients to perform gradient updates locally while maintaining privacy. The protocol minimizes data exposure by breaking down the computation into smaller, secure steps. The core claim is that existing DP mechanisms in FL are often computationally expensive. The proposed mechanism combines differential privacy with secure multi-party computation (SMPC) to perform gradient updates locally without revealing individual client data, utilizing a layered SMPC protocol for enhanced efficiency. This offers a practical and efficient solution for deploying DP in FL. The theoretical analysis demonstrates that our approach can achieve a desired privacy budget while significantly reducing the computational burden compared to standard DP techniques. This work contributes a new method to improve the performance of DP in FL.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper proposes a novel decentralized federated learning (DFL) system designed to address the critical challenges of privacy and accountability inherent in collaborative learning environments. The system leverages the strengths of three key technologies: decentralized learning, differential privacy, and blockchain auditing. Traditional federated learning, while improving privacy by training models locally, still relies on a central server for aggregation, creating a single point of failure and potential vulnerability. This proposed architecture eliminates the central server, distributing the learning process across multiple participants. Differential privacy mechanisms are incorporated to further protect individual data contributions, adding noise to the model updates to obscure sensitive information. Finally, a blockchain-based auditing system provides a transparent and immutable record of all model updates, ensuring accountability and allowing for verification of the learning process. This combination offers a robust, secure, and auditable solution for distributed machine learning. The system's core claim is that ensuring privacy and accountability in federated learning is a major challenge, and this architecture directly addresses this need.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources, primarily located at edge devices. However, the inherent distributed nature of FL introduces significant challenges, particularly regarding privacy vulnerabilities and substantial communication overhead. This paper proposes a novel framework for distributed learning with differential privacy tailored for federated edge computing environments. The core idea is to integrate a customized differential privacy mechanism with a hierarchical learning structure and adaptive privacy budgets, all while exploiting hardware-accelerated cryptographic techniques to reduce communication costs. Our approach aims to simultaneously mitigate privacy risks and improve the efficiency of FL deployments across geographically diverse edge devices. We define the following key components: (1) A hierarchical learning structure consisting of local and global layers; (2) A novel differential privacy mechanism utilizing homomorphic encryption and secure multi-party computation; (3) Adaptive privacy budget allocation based on device heterogeneity and data sensitivity. The system is designed to minimize communication, maximize privacy, and improve the overall performance of FL in resource-constrained edge environments. The proposed method provides a theoretical framework for achieving strong privacy guarantees while maintaining reasonable communication costs.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources, such as Internet of Things (IoT) devices, without directly exchanging raw data. However, the practical deployment of FL in IoT environments is hindered by several key challenges, including significant data heterogeneity across devices and the limited computational and storage resources inherent in these devices. This paper proposes a novel distributed learning framework that addresses these limitations by incorporating personalized experience replay (PER). PER allows each IoT device to store a representative subset of its training data and periodically replay past experiences to refine its local model. This mechanism not only mitigates the effects of data heterogeneity but also improves model convergence and accuracy, particularly in scenarios where individual devices have sparse or biased data. The proposed approach maintains user privacy by operating locally on device data, and the distributed nature of the framework reduces the communication overhead typically associated with FL. We demonstrate the effectiveness of our approach through a theoretical analysis and outline the key components and design considerations for a practical implementation. The core claim is that federated learning in IoT devices faces challenges with data heterogeneity and limited computational resources. The core mechanism is to implement a distributed learning framework incorporating personalized experience replay, where each IoT device stores a subset of its training data and periodically replays experiences to improve model performance, while preserving user privacy. This approach represents a significant advancement in FL for IoT, enabling more robust and accurate models in resource-constrained 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, preserving data privacy. However, the inherent data heterogeneity across clients introduces a significant challenge: algorithmic bias. This paper presents a novel method for detecting and quantifying bias within the federated learning process. Our approach leverages statistical measures and differential privacy techniques to monitor model updates and identify bias amplification. We define key metrics such as variance of model updates, divergence between client models, and the sensitivity of model predictions to sensitive attributes. The core of our method is the adaptive adjustment of learning rates based on these metrics, aiming to mitigate bias while maintaining model convergence. We demonstrate the effectiveness of our approach through a theoretical analysis and a conceptual framework, highlighting its potential for robust and fair FL systems. The proposed framework provides a quantifiable assessment of bias risk and suggests strategies for bias mitigation during the training process.
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 sharing the data itself. However, existing FL systems face significant vulnerabilities, including malicious participant attacks and data breaches. This paper proposes a novel decentralized federated learning framework that integrates Byzantine fault tolerance (BFT) protocols, inspired by blockchain technology, with differential privacy (DP) mechanisms. The core claim is that this synergistic combination provides a substantially more robust and secure FL paradigm. Specifically, the system utilizes BFT to detect and mitigate malicious behavior from participants, ensuring data integrity and model robustness, while DP safeguards user privacy by adding controlled noise to the model updates. This framework allows the system to tolerate a certain number of Byzantine failures while maintaining accurate models. The system architecture is decentralized, eliminating a single point of failure and enhancing overall resilience. We demonstrate the potential of this approach through a theoretical analysis and outline a conceptual implementation strategy.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated learning (FL) has emerged as a promising paradigm for training machine learning models on decentralized data sources without directly exchanging the raw data. However, the application of FL to graph analytics, particularly when dealing with sensitive graph data, presents significant challenges due to the inherent privacy risks associated with sharing graph structures and node attributes. This paper proposes a novel distributed federated learning framework incorporating differential privacy (DP) to address these challenges. The framework leverages secure aggregation techniques to minimize information leakage during model aggregation and integrates local differential privacy mechanisms at the node level to provide robust privacy guarantees. We demonstrate the feasibility and effectiveness of this approach through a theoretical analysis and conceptual design, highlighting its potential to enable collaborative graph analytics while preserving the privacy of participating nodes. The key contributions of this work include a tailored FL architecture for graph data, the integration of DP for enhanced privacy, and a discussion of the trade-offs involved in balancing privacy and model accuracy.
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 models often operate under the assumption of homogeneous data distributions, which frequently doesn't hold true in real-world scenarios. This research investigates a novel framework for context-aware federated learning that addresses this limitation by integrating local contextual information alongside differential privacy mechanisms. The core claim is that incorporating context allows for more accurate model aggregation, while differential privacy safeguards user data. The proposed system designs a federated learning architecture that dynamically adjusts model updates based on device-specific context and employs differential privacy to mitigate privacy risks. We demonstrate the potential of this combined approach to achieve higher model accuracy and enhanced privacy protection compared to standard FL methods. This work contributes to a more robust and practical distributed learning paradigm suitable for diverse and heterogeneous data environments.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
