federated learning

Land subsidence hazard mapping using a federated learning architecture with satellite and local environmental data

Land subsidence has become one of the most critical environmental and geomorphological hazards in recent years, threatening groundwater resources, urban infrastructure, and ecosystem stability. This study presents a novel Federated Learning (FL)-based framework for land subsidence hazard mapping in Poldokhtar County, Iran, without requiring direct access to centralized raw data. The proposed framework integrates Interferometric Synthetic Aperture Radar (InSAR)-derived subsidence rate maps from Sentinel-1 time-series data (2015–2025) with 13 environmental conditioning factors across multiple spatial clients. Five machine learning and deep learning algorithms Random Forest (RF), Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), Deep Neural Network (DNN), and Logistic Regression (LR) were employed as local base models within the FL framework, using FedAvg and FedProx aggregation strategies. The results revealed generally weak to moderate correlations between subsidence and individual environmental factors, highlighting the complex and multi-factorial nature of the subsidence process. Client-based data distribution analysis confirmed a non-IID (Non-Independent and Identically Distributed) condition, with Client 1 representing severe subsidence areas (wider range of negative values) and Client 3 representing areas with weak or negligible subsidence (narrower range near zero). Among the global federated models, RF achieved the highest accuracy (R 2 = 0.963), followed closely by LSTM (R 2 = 0.956) , demonstrating their strong capability in capturing complex spatiotemporal patterns. In contrast, LR exhibited the poorest performance (R 2 = 0.375) with the highest error rates, confirming its limitation to linear relationships. Feature importance analysis identified Digital Elevation Model (DEM), groundwater level, and soil type as the most influential predictor variables associated with subsidence risk in the study area. The findings demonstrate that the proposed FL-based framework not only enhances prediction accuracy through collaborative learning across distributed clients but also preserves data privacy by avoiding raw data sharing. This approach offers a scalable and effective decision-support tool for sustainable groundwater management and land-use planning in subsidence-prone regions.

A hierarchical privacy-aware learning framework for real-time quantification of distributed PV active power flexibility

Age‐Aware Energy and Resource Optimization for Federated Air Quality Monitoring With UAVs

ABSTRACT Reliable air quality monitoring in Internet of Things (IoT) systems requires a synergy between energy‐efficient data collection, data freshness and scalable learning across geographically distributed sensors. We propose AERO‐Air (Age‐aware Energy and Resource Optimization), a novel hierarchical framework that jointly optimizes Unmanned Aerial Vehicle (UAV) trajectories, Age‐of‐Information (AoI)‐aware client scheduling and hierarchical federated aggregation. By focusing on the temporal relevance of environmental data, AERO‐Air improves prediction accuracy, information freshness and UAV energy efficiency. The framework leverages lightweight local neural models at ground sensors, performs intermediate aggregations at follower UAVs, and utilizes a leader UAV to coordinate global updates via hierarchical Federated Learning (FL). The optimization problem, which jointly considers UAV mobility, AoI constraints and federated learning objectives, is addressed through a hybrid solution combining offline successive convex approximation (SCA) and online reinforcement learning (RL). Simulation results on the University of California Irvine (UCI) Air Quality dataset confirm that AERO‐Air significantly reduces AoI, accelerates learning convergence, and maintains high energy efficiency compared to existing baselines.

Differential Privacy for Federated Learning with Adaptive Noise

Federated learning (FL) presents a promising paradigm for training machine learning models on decentralized data sources without directly exchanging the data itself. However, the inherent privacy risks associated with aggregating model updates introduce significant challenges. Traditional differential privacy (DP) techniques often rely on adding uniform random noise to gradients, which can be overly conservative and degrade model accuracy. This paper introduces an adaptive noise scheme for FL that dynamically adjusts the noise level based on the sensitivity of the aggregated gradients. The proposed method monitors gradient variance and employs a stochastic gradient descent (SGD) variant with a dynamically adjusted learning rate and noise scale. We demonstrate through theoretical analysis and a simplified simulation that this approach significantly reduces the overall noise level compared to standard DP while maintaining a comparable privacy guarantee, ultimately leading to improved model accuracy in FL settings. The key contribution lies in the intelligent adaptation of noise, responding directly to the data's inherent characteristics.

zk-DEAP-artifact-1.0

Secure aggregation requires operating on private inputs while preserving confidentiality, verifying that each input satisfies constraints, and avoiding trusted parties. This scheme appears in federated learning, as well as Internet of Things, operational technology, blockchain, smart-grid, and voting deployments. Existing protocols achieve at most two of these requirements. We present zk-DEAP, a protocol combining lifted ElGamal homomorphic encryption, FROST threshold cryptography, and zero-knowledge proofs (Bulletproofs, zk-SNARKs, or zk-STARKs) for fully decentralized, verifiable, privacy-preserving aggregation.Our core technical contribution is a cryptographic binding mechanism preventing substitution attacks, where a valid proof for one input is paired with a ciphertext encrypting a different, malicious value. For Bulletproofs, we bind via ciphertext-derived randomness modification. For zk-SNARKs/zk-STARKs, to bind across algebraic structures, a well-known challenge in practical cryptography, we introduce a sophisticated blinded arithmetic hash commitment with an embedded Schnorr constraint, forcing the ZKP's private witness to equal the encrypted value, ensuring any circuit-verified constraint applies to the ciphertext.We implement three production-ready, defense-in-depth variants in Rust and evaluate across 5-500 participants on Azure VMs. Compared to unverified aggregation, zk-DEAP adds modest overhead while providing cryptographic guarantees against input manipulation that statistical defenses cannot match. Results show Bulletproofs, despite limited flexibility, achieve the fastest proof generation, while zk-STARKs provide post-quantum security with larger sizes, and zk-SNARKs achieve a middle ground.

Zero-Knowledge Governance: Cryptographic Compliance Auditing for Federated Edge AI

The rapid expansion of Federated Learning (FL) within Edge AI has enabled decentralized networks to collaboratively train sophisticated models without sharing raw, privacy-sensitive data [8]. However, this strict adherence to data privacy creates a significant "blind spot" for AI governance. Under emerging regulatory frameworks like the EU AI Act, regulators require proof of data safety, bias mitigation, and privacy preservation [4]. The current paradigm forces a paradox: regulators cannot verify whether individual edge nodes complied with these laws without violating the very privacy FL is designed to protect. In this paper, we propose a novel Zero-Knowledge Governance (ZKG) framework. By integrating Zero-Knowledge Succinct Non-Interactive Arguments of Knowledge (zk-SNARKs) into the local edge training phase, edge devices can cryptographically prove that their local datasets and model updates comply with encoded governance policies, without ever revealing the underlying data [1]. We present the architectural design of ZKG, analyze the vulnerabilities it addresses in decentralized AI, and propose optimizations to make cryptographic auditing viable for resource-constrained edge hardware.

A perspective on federated foundation models in biomedical sensing and imaging

In this perspective paper, we introduce multimodal multi-task federated foundation models (M3T FedFMs) as a paradigm for privacy-preserving and distributed learning over biomedical sensing and imaging data. We outline their architecture, applications across medical sectors, key challenges, and future research directions, as well as the metrics and datasets that can facilitate their benchmarking.

Training Without Gathering the Data: A Contemporary Synthesis Review of Federated Learning and Privacy-Preserving AI

This article presents a narrative review of Federated Learning and Privacy-Preserving AI in the context of Artificial Intelligence. The literature on this topic has expanded substantially over recent decades, yet it remains fragmented across subfields, methods, and national research traditions. Drawing on an interpretive synthesis of representative contributions, the review reconstructs the historical development of the area, examines the conceptual foundations and definitional disputes that organize its debates, and maps the contemporary landscape of research, including the methodological shift toward data-intensive approaches and the institutional pressures that shape publication practice. Particular attention is given to the role of federated learning and privacy as organizing themes, and to the conditions under which findings from different research traditions can be brought into productive comparison. The review identifies three synthetic conclusions: the literature is cumulatively strong but organizationally weak; methodological pluralism is better understood as a resource than as a defect; and the growing practical salience of the topic raises the stakes of its unresolved conceptual questions. An agenda for future work is proposed, emphasizing integrative research designs, transparent synthesis practices, and the protection of definitional and infrastructural work on which cumulative progress depends. The article is intended as both a reference map for newcomers and a provocation for specialists in Artificial Intelligence.

FedSCORE-PP: A Federated and PrivacyPreserving Machine Learning Framework for Collaborative Supply Chain Risk Prediction Across Organizations

Global supply chains are increasingly exposed to disruptions whose effects propagate across organizational boundaries, yet the data needed to predict such risks is fragmented among firms reluctant to share it for competitive, contractual, and regulatory reasons. Centralized machine learning therefore under-utilizes collective evidence, and organizations with inadequate datasets cannot predict risk reliably on their own [1].

Transformer-Based Federated Learning for Adaptive Multi-Stage Constant Current Charging (MSCCC) of Li-ion, NiCd, and NiMH Batteries

Reproducibility Package for "Federated Learning-enabled Intrusion Detection System (FL-IDS) with Differential Privacy for Resource-Constrained IoT Networks"

This repository contains the source code, executed notebook, experimental configurations, seed-level results, privacy-accounting outputs, clipping diagnostics, preprocessing metadata and supporting materials for the study “Federated Learning-enabled Intrusion Detection System (FL-IDS) with Differential Privacy for Resource-Constrained IoT Networks.” The package supports reproduction of the official UNSW-NB15 federated benchmark and the duplicate-safe full-corpus evaluation described in the manuscript. The original UNSW-NB15 dataset is not redistributed. File names, SHA-256 hashes, preprocessing procedures, model-training seeds and privacy-accounting assumptions are provided to support independent reproduction.

A Federated Deep Learning Framework for Privacy-Preserving IoT-Based Healthcare Monitoring Systems

Continuous, remote patient monitoring is now practically possible thanks to the expanding use of wearable and bedside sensors enabled by the Internet of Things (IoT). However, the centralised aggregation of physiological data needed by traditional deep learning pipelines presents significant privacy, legal, and bandwidth issues. In order to build a shared diagnostic model across dispersed IoT healthcare nodes without sending raw patient data to a central server, this study suggests a federated deep learning (FDL) system. The framework integrates a FedAvg/FedProx aggregation scheme at the server with a lightweight hybrid convolutional neural network and bidirectional long short-term memory (CNN-BiLSTM) architecture for local physiological-signal feature extraction. Differential privacy (DP) noise injection and secure aggregation are added to prevent information leakage from shared gradients. We present a simulation-based evaluation intended to characterise the expected accuracy, communication-efficiency, and privacy-utility trade-offs of the framework in comparison to centralised and local-only baselines. We also describe the end-to-end system architecture, the on-device training and communication protocol, and the privacy-accounting method. The results show that the suggested federated strategy can reduce per-round communication volume by an order of magnitude, eliminate the need to transmit raw sensor data, and approach centralized-training accuracy within a narrow margin. We also examine how the differential-privacy budget affects model utility and talk about unresolved issues with adversarial robustness, device and network heterogeneity, and statistical heterogeneity (nonIID data). The suggested approach provides a workable blueprint for scalable, privacypreserving, and regulator-compliant AI-based healthcare monitoring at the network edge.