Federated Learning (FL) offers a promising paradigm for training machine learning models on decentralized data sources without directly exchanging data. However, existing FL frameworks are susceptible to various vulnerabilities, including privacy breaches through information leakage and attacks from Byzantine clients attempting to compromise the learning process. This paper proposes a novel distributed FL framework that integrates differential privacy (DP) and Byzantine fault tolerance (BFT) mechanisms to address these challenges comprehensively. Our approach employs advanced DP techniques to rigorously limit the information revealed by individual clients during model updates, while simultaneously utilizing BFT algorithms to detect and mitigate the influence of malicious or faulty clients. The resulting system demonstrates improved security, enhanced privacy guarantees, and robustness against adversarial attacks, making it a significant advancement in the field of secure and reliable distributed learning. The core of our work lies in the synergistic combination of these two crucial techniques, providing a layered defense against potential threats in FL environments. We detail the mathematical formulations underlying our approach and provide a theoretical analysis of its performance.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Abstract Several classifiers operate exclusively on discrete variables, requiring continuous attributes to be preprocessed through discretization. Supervised discretization addresses this need by partitioning the domain of continuous variables into intervals that define a discretization policy. Federated learning, in turn, enables the collaborative training of global models without sharing raw data: users train local models and communicate their parameters to a central server, which aggregates them into a global model. A key challenge in this setting is achieving performance comparable to centralized methods while minimizing communication overhead. In this work, we propose a federated discretization framework that computes a global discretization policy in a single communication round. Each user estimates Gaussian mixture models for the continuous variables and transmits their parameters-referred to as representatives-to the server. The server then applies a discretization algorithm to these representatives to derive a global policy, which is subsequently distributed back to the users. The proposed framework accommodates multiple discretization strategies; specifically, we present federated adaptations of equal-width, equal-frequency, entropy-based, and kernel density-based methods. Experiments conducted on ten benchmark datasets demonstrate that the proposed framework achieves performance comparable to centralized discretization approaches, with the kernel density-based and equal-frequency variants yielding the most competitive results.
José Luis Flores, Borja Calvo, Aritz Pérez· Data Mining and Knowledge Di...· 0 citations
This paper presents a novel approach to distributed graph learning utilizing Federated Bayesian Networks (FBNs). The core challenge in training large graph neural networks (GNNs) lies in the substantial computational resources required, often necessitating centralized training environments. Federated Bayesian Networks offer a decentralized solution, enabling learning across multiple clients without direct data sharing. The proposed method involves local training of Bayesian Networks on individual client graph subsets, followed by parameter aggregation by a central server to refine a global Bayesian Network model. This architecture addresses the limitations of traditional GNN training while prioritizing data privacy and mitigating computational demands. The key innovation lies in the synergistic combination of federated learning principles with the probabilistic inference capabilities of Bayesian Networks, resulting in a robust and scalable framework for distributed graph learning. This approach demonstrates the potential for efficient learning from decentralized graph data sources.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper presents a novel approach to decentralized federated learning that leverages the strengths of differential privacy and homomorphic encryption to achieve robust privacy guarantees. The core idea is to encrypt each participant's local data using homomorphic encryption, allowing a central server to perform computations directly on the encrypted data without ever needing to access the plaintext. Subsequently, the encrypted results are sent back to the participants. This architecture effectively mitigates privacy risks associated with traditional federated learning methods. The combination of these three technologies – federated learning, differential privacy, and homomorphic encryption – provides a powerful framework for secure and decentralized machine learning. We demonstrate the potential for achieving strong privacy guarantees while maintaining the benefits of distributed learning.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without directly exchanging the data itself. However, existing FL systems are susceptible to Byzantine attacks, where malicious participants can inject faulty model updates, compromising the global model's integrity. This paper proposes a novel decentralized federated learning framework incorporating Byzantine Fault Tolerant (BFT) consensus protocols. Our system utilizes cryptographic consensus mechanisms to validate and authenticate model updates from each participant before aggregation, thereby mitigating the risks posed by Byzantine nodes. The core innovation lies in the integration of FL with robust BFT consensus, ensuring secure and reliable model training even when faced with adversarial behavior. We introduce a framework utilizing verifiable computation and consensus-based proofs to achieve this. This approach allows for the detection and rejection of malicious updates, ultimately leading to a more trustworthy and resilient global model. The system is designed for scalability and adaptability, addressing key challenges in practical FL deployments. The key mathematical concepts underlying the system are represented through the following notation: (x_i, m_i), where x_i represents the data sample from participant i, and m_i represents the model update generated by participant i. The aggregation function is denoted as (Σ_{i=1}^K (α_i * m_i)), where α_i represents the learning rate for participant i, and K is the total number of participants. The BFT consensus protocol relies on a threshold number of participants (T) to reach agreement, and the proof of correctness is represented as P(m_true, m_agg), where m_true is the true global model, and m_agg is the aggregated model. Byzantine faults are represented as f_i, where f_i is the faulty model update from participant i. The probability of a successful consensus is denoted as P_success. The security level is characterized by the parameter β, representing the probability of successfully detecting a Byzantine update.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
The rapid expansion of IoT deployments has created an attack surface that conventional intrusion detection systems are ill-equipped to defend.Centralized deep learning approaches compromise data privacy, while existing federated methods stop detection without addressing what the network should do next.This paper proposes a twostage framework that closes both gaps.In Stage 1, a federated CNN-BiLSTM-SGB model trained across eight non-IID clients produces a calibrated attack probability per flow, achieving a ROC-AUC of 0.9950 and an attack F1-score of 0.9924 on the CIC IoT Dataset 2023.In Stage 2, a dueling DDQN agent conditioned on that probability selects among six operational responses under the ATSR reward function, which weights penalties by attack severity and detection confidence.The agent reached a primary action accuracy of 97.73% and an attack-ALLOW rate of just 1.04%, with the highest accuracy recorded for the most dangerous threat categories.Together, the two stages demonstrate that federated data-local intrusion detection and severity-aware automated response can operate within a single coherent pipeline.
Anaam Ghanim Hilal, Nawfal Turki Obeis· International Journal of Int...· 0 citations
This review provides a comprehensive synthesis of traditional and artificial intelligence (AI)-based techniques across the complete autonomous UAV navigation pipeline, including environmental perception, localization and mapping, path planning and obstacle avoidance, and motion control. It systematically examines recent advances in computer vision, SLAM, deep reinforcement learning, transformer-based methods, multimodal sensor fusion, and intelligent control, together with commonly used datasets, simulation platforms, and evaluation practices. The comparative analysis identifies hybrid AI architectures as the most promising direction for practical autonomous UAV navigation, as they combine the reliability and interpretability of conventional navigation methods with the adaptability and learning capabilities of AI-based approaches. The review further identifies computational and energy constraints, safety and explainability, robust multimodal sensor fusion, cybersecurity, and simulation-to-real transfer as major barriers to large-scale real-world deployment. Emerging technologies, including foundation models, vision-language models, edge AI, federated learning, digital twins, and swarm intelligence, are also examined as potential enablers of next-generation UAV autonomy. By integrating these findings across perception, localization, planning, and control within a unified framework, this review clarifies the current technological trade-offs, highlights the key barriers to real-world deployment, and provides specific research priorities for developing safe, adaptive, computationally efficient, and scalable autonomous UAV navigation systems.
Taha Mahmood, Ali Ahmed Mirza· Scientific journal of engine...· 0 citations
This paper explores the application of federated learning (FL) as a novel approach to privacy-preserving data analysis. Traditional data analysis methods often require centralized data collection, raising significant privacy concerns. Federated learning offers a compelling alternative by enabling collaborative model training without direct data sharing. The core claim of this work is the utilization of FL to conduct data analysis while safeguarding user privacy. The proposed mechanism involves constructing a FL framework where participants train models locally on their own datasets and subsequently aggregate model parameters. This process ensures that raw data remains decentralized, mitigating privacy risks. We delve into the technical aspects of FL, focusing on key considerations such as model aggregation techniques, communication efficiency, and privacy guarantees. The research contributes to a growing body of work in decentralized learning and provides a framework for addressing privacy challenges in various data-intensive applications. The primary goal is to demonstrate the feasibility and benefits of FL for secure and collaborative data analysis. ---
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper presents a novel approach to generative modeling by integrating Generative Adversarial Networks (GANs) with Federated Learning (FL). Traditional GAN training suffers from centralized data requirements and privacy concerns. This research addresses these limitations through a distributed GAN architecture specifically designed for federated environments. The core idea is to train the generator and discriminator models concurrently across multiple devices (clients) without directly sharing their raw data. Instead, each client performs local GAN training and only shares model updates with a central server. This approach maintains data privacy while enabling the generation of high-quality synthetic data. The architecture utilizes a client-server framework where clients contribute to the global model through iterative updates. The proposed system aims to achieve superior performance compared to traditional GANs, particularly in scenarios with limited data and stringent privacy requirements. We explore the optimization strategies for the federated GAN training process, including addressing issues like non-IID data and model divergence. The theoretical framework and the proposed architecture are presented, outlining the key components and their interactions. Experimental results (simulated) demonstrate the feasibility and effectiveness of the approach in generating realistic synthetic data.
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, thus addressing privacy concerns. However, FL is still susceptible to privacy breaches and suffers from significant information loss during model aggregation, a phenomenon addressed by the information bottleneck (IB) principle. This paper proposes a novel framework that integrates the IB technique with differential privacy (DP) within the FL setting. We formulate the problem as a constrained optimization, minimizing information loss while simultaneously satisfying DP guarantees. Our approach utilizes a compressed representation of local data, learned through an IB objective, and introduces noise to protect individual data points, ensuring privacy. The core contribution lies in the synergistic combination of these two techniques, leading to enhanced privacy protection and improved model accuracy compared to standard FL. We demonstrate the effectiveness of our framework through a theoretical analysis and outline potential implementation strategies. The primary goal is to achieve a balance between model performance and privacy preservation, a critical aspect often overlooked in current FL methodologies. The theoretical framework provides a foundation for future research and practical deployment in privacy-sensitive applications.
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, FL systems are vulnerable to Byzantine attacks, where malicious participants can inject faulty model updates, compromising model accuracy and potentially causing significant harm. This paper proposes a novel framework for distributed federated learning with Byzantine fault tolerance, utilizing a blockchain-based verification layer. Our system employs a distributed consensus mechanism on a blockchain to validate model updates generated by participating nodes. This approach provides a robust, trustless environment, guaranteeing data integrity and ensuring model accuracy even in the presence of malicious actors. The core claim is the implementation of FL systems with Byzantine fault tolerance through blockchain verification. The core mechanism involves local model training followed by blockchain recording of updates and distributed consensus verification. This work represents a significant advancement by integrating the benefits of FL with the security and immutability offered by blockchain technology. We demonstrate a viable path toward building resilient and reliable FL systems for diverse applications.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Federated Learning (FL) offers a promising paradigm for training machine learning models on decentralized data sources without directly exchanging data. However, existing FL frameworks are susceptible to various vulnerabilities, including privacy breaches through information leakage and attacks from Byzantine clients attempting to compromise the learning process. This paper proposes a novel distributed FL framework that integrates differential privacy (DP) and Byzantine fault tolerance (BFT) mechanisms to address these challenges comprehensively. Our approach employs advanced DP techniques to rigorously limit the information revealed by individual clients during model updates, while simultaneously utilizing BFT algorithms to detect and mitigate the influence of malicious or faulty clients. The resulting system demonstrates improved security, enhanced privacy guarantees, and robustness against adversarial attacks, making it a significant advancement in the field of secure and reliable distributed learning. The core of our work lies in the synergistic combination of these two crucial techniques, providing a layered defense against potential threats in FL environments. We detail the mathematical formulations underlying our approach and provide a theoretical analysis of its performance.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
