federated learning

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.

Decentralized Federated Reinforcement Learning with Byzantine Agreement

Decentralized Federated Reinforcement Learning (DFRL) presents a promising approach to training robust and adaptable RL agents by leveraging distributed data and computational resources. However, this paradigm is susceptible to attacks from Byzantine actors who can inject malicious updates, jeopardizing the learning process and potentially leading to catastrophic outcomes. This paper introduces a novel framework for DFRL that incorporates Byzantine agreement protocols to mitigate these vulnerabilities. Our approach enables agents to collaboratively learn while simultaneously resisting manipulation and ensuring convergence. We formalize the problem, define the key components of the system, and present a theoretical analysis demonstrating the effectiveness of our method. The core claim is that training RL agents across multiple devices introduces vulnerabilities to malicious actors. The core mechanism applies Byzantine agreement protocols to decentralized federated RL, enabling agents to learn collaboratively while resisting manipulation and ensuring convergence. This work significantly advances the field by providing a resilient and trustworthy solution for DFRL, opening up new possibilities for real-world deployments. ---

PNFR: practicality-enhanced and non-interactive privacy-preserving federated regressions

Abstract Federated learning is a technology that is used to protect data privacy in machine learning. Nonetheless, in federated learning, updating the global model requires the use of gradient descent algorithm, which involves multiple rounds of interaction between entities to complete the iterative updates, inevitably incurring massive computational and communication overhead. In 2020, Wang et al. first proposed a non-interactive federated regression scheme, which effectively improves the training efficiency of regression models while protecting the privacy of local training data. However, like most current federated regressions, it involves a third authority (TA) to generate keys for each entity, which poses a significant privacy risk and results in considerable communication overhead. From the view of security and practicality, this paper first proposes a multi-party homomorphic encryption algorithm named MPaillier. Furthermore, we have designed PNFR, a privacy-preserving federated learning scheme for regressions training built on the MPaillier algorithm. The participating entities of PNFR are the data owners and a cloud server, eliminating the need for a TA, thus enhancing the practicality and efficiency of the scheme. Experimental results demonstrate that our scheme is $\sim 10^{3}$ times faster than interactive federated regressions PrivFL and about 80% faster than non-interactive federated regressions VANE.

Training Without Gathering the Data: A Comparative Analysis 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.

Research on Green Supply Chain Financing Problems Empowered by Federated Learning and Blockchain

Amid the global transition toward carbon neutrality, digital technologies such as blockchain and federated learning offer a viable pathway to alleviating green financing constraints for small- and medium-sized enterprises (SMEs) and advancing supply chain decarbonization. Against this backdrop, this paper proposes a digital intelligence-driven financing model for green supply chains. A dynamic game model is developed to capture strategic interactions between financial institutions and SMEs in financing mode selection and credit decisions, with an evolutionary game-theoretic approach within a two-layered complex network subsequently employed to examine how key factors shape evolutionary outcomes. The results reveal that the federated learning and blockchain-enabled green supply chain financing model reshapes traditional services via digital credit construction, markedly improving lending willingness, lowering default probabilities, and deterring greenwashing. Additionally, technology usage costs, federated training incentives, and data breach risks are identified as critical determinants of bilateral financing mode choices.

Training Without Gathering the Data: A Interdisciplinary Mapping 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.

Training Without Gathering the Data: A Interdisciplinary Mapping 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.

Agentic GAN-driven federated resource orchestration for music streaming in edge-cloud collaborative consumer electronics networks

Review of: "Advancing Personal Health Data Spaces: Governance, Interoperability, and Real-World Evidence for Learning Healthcare Systems"

This manuscript presents a timely, ambitious, and highly relevant commentary on the role of Personal Health Data Spaces in the future development of healthcare.I appreciate its patient-centred perspective and its recognition that personalised medicine cannot be achieved through isolated technological solutions, fragmented clinical information, or disconnected research initiatives.The manuscript addresses a sensitive but fundamental problem: healthcare systems are still often organised in professional, institutional, and data-related silos.In practice, individual clinical units, specialists, and researchers may work with considerable expertise, but too often within separate perspectives and infrastructures.This can lead to duplication, incomplete understanding of the patient journey, inconsistent data use, and missed opportunities for collaboration.From my own professional experience, I recognise this fragmentation.Major clinical and scienti c questions are rarely solved by a single specialty, clinic, institution, or data source.The development of meaningful personalised treatment requires integration across clinical disciplines, longitudinal patient data, imaging, laboratory and genomic information, patient-reported outcomes, real-world evidence, and rigorous analytical methods.A particular strength of the manuscript is its distinction between Personal Health Data Spaces and related concepts such as the European Health Data Space, federated data infrastructures, real-world evidence platforms, and learning healthcare systems.

Decentralized Verification of Federated Learning Models

Federated Learning (FL) has emerged as a promising paradigm for training machine learning models on decentralized data sources without direct data sharing. However, ensuring the integrity and accuracy of these models remains a significant challenge. Traditional verification methods often rely on centralized aggregation, inherently compromising user privacy and introducing a single point of failure. This paper proposes a novel blockchain-based system for decentralized verification of FL models. The system leverages cryptographic proofs, specifically zero-knowledge Succinct Non-Interactive Argument of Knowledge (zk-SNARKs), allowing nodes to independently verify model updates without revealing the underlying data. This approach eliminates centralized aggregation, enhancing privacy and establishing a verifiable, distributed ledger of model updates. The core claim is that current decentralized verification methods are computationally expensive and rely on centralized aggregation, thus, this system offers a truly decentralized and privacy-preserving verification framework.

Replication package for Flows and Rounds: benchmark and retrieval scripts for distributed neurodynamic optimization and federated learning

This package contains the code and generated data behind the quantitative results of the survey "Flows and Rounds: A Survey of Distributed Neurodynamic Optimization and Federated Learning", submitted to Neurocomputing. It reproduces every number, table, and figure in Sections 2.3 and 8 of the article. No third-party, proprietary, or personal data is involved: all data is synthetic and generated at run time from fixed random seeds, so the package is self-contained and deterministic. Two scripts are included. The first, toy_benchmark.py, runs a controlled experiment on a synthetic distributed optimization problem with five nodes, twenty dimensions, and a closed-form optimum, averaged over ten seeds. It measures two things. Experiment one measures consensus drift as a function of the number of local steps per communication round, holding total local work fixed, and tests the prediction that drift grows with the dwell interval and vanishes when the agents hold identical objectives. Drift is found to be identically zero without gradient dissimilarity and to grow as E^0.88 and E^0.84 at the two heterogeneity levels tested. Experiment two measures whether an integral-enhanced flow, of the kind used in the zeroing neural network literature to reject persistent disturbance, also attenuates the Gaussian noise that a differential privacy mechanism deliberately injects. Both flows are driven by an identical noise stream and the noise response is isolated by differencing each noisy run against its own noise-free run. The integral term is found to remove steady-state bias almost entirely while leaving injected-noise energy unchanged, a ratio of 1.007. This second result contradicted the authors' expectation when the experiment was designed, and it is reported as measured. The second script, search_protocol.py, records a structured literature retrieval executed on 31 August 2026 and computes the deduplication and overlap counts reported in Section 2.3 of the article. It also emits a screening sheet listing all eighty-five retrieved records with their query provenance. The package is intended for readers who wish to verify the article's numerical claims, and for anyone extending the benchmark to other flows, noise models, or heterogeneity regimes. It requires only Python, NumPy, and Matplotlib.

A proactive defense framework for federated learning: A framework integrating verified piecewise perturbation and quantum-enhanced encryption