federated learning

Resilient Multi-Layer LSTM Digital Twin Framework for Athlete Logistics and Safety in 6G

The development of 6G communication technologies provides new possibilities for the integration of advanced intelligence, connectivity, and security in sports and athlete management. In this paper, a Federated AI and Privacy-Preserving Digital Twin system (FPP-DT) is presented to optimize athlete logistics, performance monitoring and safety in real time. Dynamic virtual models of the athlete (digital twins) are used to gather physiological, environmental and logistical data by means of wearable sensors and smart devices. Such replicas support predictive analytics, proactive risk assessment, and adaptive decision-making, thereby optimizing training, transportation, and emergency response. Federated AI prevents the centralization of raw biometric and other personal data by training a model using the sensors of athletes’ devices and clubs, as well as the medical institutions. Privacy protection under collaborative learning is further improved using security techniques, such as differential privacy and secure multi-party computation. The ultra-low latency and extremely high reliability aspects of 6G networks provide the seamless connectivity needed for real-time digital twins’ synchronization and stimulus-free transmission of information between athletes, coaches, medical staff, and event organizers. Thus, the system addresses the key problem areas in the management of athletes in terms of constant control over safety, the proper organization of logistics, and performance forecasting reinforcement, without compromising the privacy of the personal information. This can also be applied to international sporting events such as the Olympics, professional sports associations and training programs, where intelligent and safe systems are highly applicable to the safety of the athletes.

FedHC-GNN for Federated Multimodal Representation Learning of Cross-Modal Disclosure Consistency in Online Charity Transparency Assessment

Privacy-Preserving Intrusion Detection via Federated Learning: An Empirical Evaluation with Automated Response Recommendation

Distributed Federated Learning with Byzantine Fault Tolerance using Homomorphic Encryption

Federated learning (FL) offers a promising approach to training machine learning models across decentralized devices while preserving data privacy. However, FL systems are vulnerable to Byzantine faults, where malicious participants introduce corrupted model updates, compromising the integrity of the global model. This paper proposes a novel framework for distributed federated learning with Byzantine fault tolerance, leveraging the power of homomorphic encryption. The system encrypts model updates using homomorphic encryption, allowing the central server to perform aggregation computations directly on the encrypted data. This approach eliminates the need for decryption, thereby safeguarding client data and providing robust protection against Byzantine attacks. The core claim of this work is that the combination of FL with homomorphic encryption provides a fundamentally secure and resilient solution for distributed model training. We detail the system architecture, the encryption and aggregation protocols, and analyze the security and performance implications. The proposed method significantly enhances the robustness of FL against malicious participants, offering a practical solution for privacy-sensitive applications.

Distributed Learning with Federated Generative Adversarial Networks

This paper presents a novel framework for distributed learning of Generative Adversarial Networks (GANs) through a federated learning approach. Traditional GAN training demands centralized computation and large-scale datasets, posing significant challenges for privacy-sensitive and resource-constrained environments. This research addresses these limitations by enabling collaborative GAN training across multiple decentralized devices, termed as Federated Generative Adversarial Networks (FedGANs). The core claim is that training GANs across distributed devices presents substantial challenges, and this paper proposes a framework to overcome these challenges. The framework leverages federated learning to allow devices to generate data collaboratively without sharing raw data, thereby preserving data privacy. The design focuses on maintaining the integrity and diversity of generated samples. This work introduces a new approach to federated learning specifically optimized for GANs, contributing to the advancement of privacy-preserving and decentralized generative modeling. The proposed system is evaluated conceptually, outlining the key components and potential improvements.

Algorithmic Fairness via Randomized Smoothing in Federated Learning

Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without directly exchanging data. However, the inherent data heterogeneity and potential biases present in these datasets pose significant challenges to achieving algorithmic fairness. This paper investigates the application of randomized smoothing, a technique traditionally used in batch learning, to mitigate bias and improve fairness in federated learning settings. We propose a novel framework that adapts randomized smoothing to the asynchronous and decentralized nature of FL. The core idea is to introduce controlled noise during model aggregation, effectively averaging out biased updates from clients with differing data distributions. Our approach demonstrates improved fairness metrics compared to standard federated averaging, particularly in scenarios with significant data skew. We formally define the problem, outline the methodology, and discuss the theoretical implications of our findings. This work represents a new direction in fairness-aware federated learning and contributes to the development of more robust and equitable machine learning systems.

"Processed Results for Low-Visible Robust Federated Learning"

"This dataset contains the processed experimental results and figure-source files associated with the study \u201cLow-Visible Robust Weight Generation for Byzantine Federated Learning via Sketch-Based Detection.\u201d The data support the evaluation of CipherSketch-RFL under Byzantine model-update attacks, including sign flipping, scaling, model replacement, A Little Is Enough, and inner product manipulation. The package includes multi-seed accuracy summaries, Byzantine weight statistics, visibility-sensitivity results, protected-backend verification records, and source data for the manuscript figures. MNIST, Fashion-MNIST, and CIFAR-10 are public benchmark datasets and are not redistributed. They can be downloaded automatically through torchvision using the accompanying code package. The processed results are provided in CSV and JSON formats for inspection and reproduction."

Computational Heterogeneous-Response Pharmacology (CHRP): A Formalized Framework for Embodied Pathology-Guided Individualized Drug Verification 计算异质性响应药理学验证理论(CHRP):基于具身病理学思想的个体用药显性验证形式化框架

Contemporary pharmacology remains anchored to a population-centric epistemology, wherein the "average patient" derived from randomized controlled trials (RCTs) serves as the gold standard for dosing and therapeutic decision-making. This framework systematically marginalizes individual heterogeneity in drug response, treating deviation from the mean as statistical noise rather than ontologically significant signal. This manuscript presents the **Computational Heterogeneous-Response Pharmacology (CHRP)** framework, a formalized theoretical architecture for individualized drug verification grounded in the philosophy of **embodied pathology**. CHRP advances three core axioms: (1) individual pharmacological heterogeneity constitutes an ontological reality, not merely measurement error; (2) patient-reported outcomes (PROs) possess epistemic parity with objective biomarkers; and (3) individual drug responses are computationally predictable through multi-scale modeling. From these axioms, CHRP derives a **three-level verification closure**: micro-level digital twin calibration with micro-dosing; meso-level N-of-1 adaptive trials with Bayesian response algorithms; and macro-level federated learning regulatory networks that preserve data sovereignty. The framework distinguishes contextual implementation pathways: developed economies may leverage full digital twin infrastructure and electronic health record integration, while developing regions can deploy lightweight federated learning nodes without raw data leakage. CHRP thus claims **global explanatory universality** at the axiomatic level while demanding **contextual adaptation** at the implementation level. **Current Status Declaration:** This manuscript presents a completed theoretical framework with formalized axioms, mechanisms, and falsifiable propositions. Large-scale multi-center N-of-1 clinical trials to empirically validate its core hypotheses are pending. CHRP is offered as a candidate paradigm for global academic discussion, falsification, and iterative refinement. **Disclaimer:** This theoretical framework does not constitute clinical guidance. All therapeutic decisions must comply with local regulatory requirements and established clinical standards. 当代药理学仍深植于一种以群体为中心的认识论:随机对照试验(RCT)所推导出的"平均患者",是剂量确定与治疗决策的黄金标准。这一框架系统性地边缘化了药物反应的个体异质性,将偏离均值的现象视为统计噪声,而非具有本体论意义的信号。 本文提出**计算异质性响应药理学验证理论(CHRP)**,一个基于**具身病理学**哲学思想的、用于个体用药验证的形式化理论架构。CHRP 提出三条核心公理:(1)个体药理学异质性构成本体论层面的实在,而非单纯的测量误差;(2)患者报告结局(PROs)与客观生物标志物具有同等认识论地位;(3)个体药物反应可通过多尺度建模进行计算预测。基于这三条公理,CHRP 推导出**三级验证闭合机制**:微观层面的数字孪生校准与微剂量探测;中观层面的 N-of-1 自适应试验与贝叶斯响应算法;以及宏观层面的联邦学习监管网络,在保护数据主权的前提下实现跨机构知识聚合。 该框架区分了情境化的实施路径:发达经济体可利用完整的数字孪生基础设施与电子健康档案整合;发展中地区则可部署轻量级联邦学习节点,无需原始数据泄露即可参与全球网络。因此,CHRP 在公理层面主张**全球普适解释力**,在实施层面要求**情境化适配**。 **当前状态声明:** 本文呈现的是一个理论框架已完成的文稿,包含形式化公理、机制设计与可证伪命题。验证其核心假设的大规模多中心 N-of-1 临床试验尚待开展。CHRP 作为候选范式,供全球学术界讨论、证伪与迭代完善。 **免责声明:** 本理论框架不构成临床指导。所有治疗决策须遵循当地监管要求与既定临床标准。

Scalable Federated Learning with Differential Privacy and Graph-Based Communication

Federated learning (FL) offers a promising paradigm for training machine learning models on decentralized data sources without directly exchanging the data itself. However, traditional FL approaches often suffer from significant communication overhead and potential privacy vulnerabilities. This research proposes a novel scalable federated learning system that addresses these limitations through the integration of graph-based communication topologies and differential privacy mechanisms. The core idea is to represent the relationships between participating clients as a graph, enabling selective communication and aggregation of model updates based on the graph structure, thereby reducing unnecessary communication and enhancing privacy. The system utilizes a graph convolutional network (GCN) to learn client embeddings reflecting their connectivity and data characteristics, which then guide the communication process. Differential privacy is incorporated by adding calibrated noise to the aggregated model updates, providing a provable privacy guarantee. Simulation results demonstrate that the proposed approach achieves significant improvements in communication efficiency and privacy compared to standard FL methods, particularly in scenarios with complex client relationships and stringent privacy requirements. This work contributes a practical and scalable solution for deploying federated learning in diverse applications where data privacy and communication efficiency are paramount.

Adaptive Differential Privacy for Federated Learning via Randomized Compression

Federated learning (FL) offers a promising paradigm for training machine learning models on decentralized data sources without directly exchanging data. However, achieving strong differential privacy (DP) guarantees in FL is a significant challenge, particularly when combined with compression techniques commonly employed to reduce communication costs. Traditional approaches often rely on fixed compression ratios, potentially sacrificing accuracy for privacy or vice versa. This paper introduces an adaptive differential privacy framework for FL that dynamically adjusts the compression ratio based on the sensitivity of the data and the desired privacy level. We leverage randomized compression methods, specifically noise addition with learned parameters, to achieve this adaptation. Our approach demonstrates a novel balance between privacy and utility, offering a more effective solution compared to static compression strategies. The core claim of this work is that achieving strong differential privacy guarantees in federated learning necessitates careful management of compression ratios. The key mechanism involves introducing an adaptive compression scheme. This paper presents a formalization of this adaptive approach, outlining its mathematical foundations and providing a framework for its implementation.

Scalable Federated Learning with Differential Privacy and Graph-Based Communication

Federated learning (FL) offers a promising paradigm for training machine learning models on decentralized data sources without directly exchanging the data itself. However, traditional FL approaches often suffer from significant communication overhead and potential privacy vulnerabilities. This research proposes a novel scalable federated learning system that addresses these limitations through the integration of graph-based communication topologies and differential privacy mechanisms. The core idea is to represent the relationships between participating clients as a graph, enabling selective communication and aggregation of model updates based on the graph structure, thereby reducing unnecessary communication and enhancing privacy. The system utilizes a graph convolutional network (GCN) to learn client embeddings reflecting their connectivity and data characteristics, which then guide the communication process. Differential privacy is incorporated by adding calibrated noise to the aggregated model updates, providing a provable privacy guarantee. Simulation results demonstrate that the proposed approach achieves significant improvements in communication efficiency and privacy compared to standard FL methods, particularly in scenarios with complex client relationships and stringent privacy requirements. This work contributes a practical and scalable solution for deploying federated learning in diverse applications where data privacy and communication efficiency are paramount.

Distributed Federated Learning with Differential Privacy for Personalized Models

Federated learning (FL) presents a promising approach to training machine learning models across decentralized devices while preserving data privacy. However, traditional FL methods often lack sufficient privacy guarantees, leaving users vulnerable to privacy breaches. This work proposes a novel framework for distributed federated learning incorporating differential privacy (DP). Our approach enhances the standard FL process by adding noise to the model updates, effectively masking individual user contributions. This guarantees a rigorous privacy budget, quantified by the ε and δ parameters of the DP mechanism. The resulting system enables personalized model training – adapting the global model to individual user data – while maintaining strong privacy protections. We outline the core components of the system, including client selection, local model training with DP noise injection, and aggregation of noisy updates. The theoretical analysis demonstrates the effectiveness of the proposed method in achieving strong privacy guarantees alongside reasonable model accuracy. The presented framework provides a viable path for building trust-worthy and privacy-preserving collaborative learning systems.