Federated learning (FL) offers a promising approach to training machine learning models on decentralized datasets without directly sharing the data itself. However, existing FL systems are susceptible to Byzantine attacks, where malicious participants can inject poisoned data or manipulate model updates, ultimately compromising the global model's integrity. This paper proposes a novel decentralized federated learning system incorporating Byzantine fault tolerance (BFT) achieved through a blockchain-based verification layer. The system leverages blockchain technology to cryptographically verify model updates from each participant before they are aggregated into the global model. This ensures data integrity and enables the detection and mitigation of Byzantine attacks. The core claim is that existing FL systems are vulnerable to these attacks. The proposed mechanism implements a decentralized FL system utilizing a blockchain-based verification layer. This represents a new approach to robust FL training. The system utilizes the following key components: participant nodes, a blockchain network, and a global model aggregator. The blockchain network is composed of multiple nodes that maintain a ledger of all model updates. The global model aggregator utilizes the blockchain network to verify model updates before aggregating them into the global model. The proposed system enhances the security and robustness of FL training by providing a tamper-proof audit trail and enabling the detection of malicious participants.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper presents a novel machine learning framework, Privacy-Preserving Personalized Multimodal Emotion Recognition (P3MER), that simultaneously addresses three fundamental challenges in affective computing: achieving state-of-the-art recognition accuracy, ensuring robust privacy protection, and enabling effective personalization to individual users. The framework integrates hierarchical multimodal fusion with federated learning and differential privacy to enable collaborative model training without centralized data collection, thereby preserving the confidentiality of sensitive biometric data such as facial expressions, speech recordings, and physiological signals. A key innovation is the incorporation of federated meta-learning that allows rapid personalization of global models to individual expression patterns with minimal local data, while maintaining formal privacy guarantees. Extensive experimental evaluation across three benchmark datasets (CMU-MOSEI, DEAP, and MAHNOB-HCI) demonstrates that P3MER achieves an average improvement of 4.1% in recognition accuracy over state-of-the-art centralized models, while providing formal \((\epsilon , \delta )\) -differential privacy guarantees. At a privacy budget of \(\epsilon = 3.0\) , the framework maintains 95.8% of the non-private federated performance, significantly outperforming conventional differentially private federated learning approaches. The meta-learning personalization mechanism yields an average personalization gain of 14.7% with only five adaptation steps, effectively addressing the inherent heterogeneity in emotional expression across individuals. Furthermore, the framework demonstrates exceptional robustness to real-world challenges, including extreme data heterogeneity (39% reduction in performance variance compared to existing personalized federated approaches), modality incompleteness (maintaining 86.3% of full-modality performance when physiological signals are unavailable), and few-shot learning scenarios (achieving 78% of maximum personalization gain with only 20-50 local samples). These results collectively validate that P3MER successfully reconciles the competing objectives of accuracy, privacy, and personalization in multimodal emotion recognition, offering a practical pathway toward deployable, ethical affective computing systems that respect user privacy while maintaining adaptive intelligence. The proposed framework establishes new standards for privacy-preserving affective computing and provides both theoretical foundations and practical implementations for developing emotion-aware technologies that earn user trust through their technical capability and ethical design. By demonstrating that privacy protection and personalization need not come at the expense of recognition accuracy, this work advances the field toward human-centered AI systems that are simultaneously intelligent, adaptive, and respectful of fundamental privacy rights.
Federated learning---the artificial intelligence whose subject is the decentralized classroom and whose lesson is the model's travel---moved from Dwork's 2006 differential privacy and Shokri and Shmatikov's 2015 gradients through Konečný's 2016 compression, McMahan's 2017 FedAvg, and Bonawitz's 2017 aggregation to Zhao's 2018 non-IID, Kairouz's 2021 survey, and Zhu's 2019 leakage. This article presents a narrative review of that arc's canonical line: Dwork's 2006 ICALP, Shokri and Shmatikov's 2015 CCS, Konečný and colleagues's 2016 strategies, McMahan, Moore, Ramage, Hampson, and Arcas's 2017 FedAvg, Bonawitz and colleagues's 2017 secure aggregation, Zhao and colleagues's 2018 non-IID, Hard and colleagues's 2018 keyboard, Zhu, Liu, and Han's 2019 gradients, Yang and colleagues's 2019 concept, Li and colleagues's 2020 convergence, Li and colleagues's 2020 challenges, and Kairouz and colleagues's 2021 advances. The review is organized around three themes: the privacy's premise and the communication's bottleneck, in which the Dwork's noise and the Shokri-Shmatikov's gradients founded the distributed's training; the algorithm's and the deployment's era, in which the FedAvg's averaging, the secure's aggregation, and the keyboard's deployment gave the federation its engine; and the heterogeneity's and the frontier's era, in which the non-IID's data, the gradient's leakage, the convergence's proofs, and the open's problems carried the field into the privacy's science. It is concluded that federated learning is the machine learning's decentralization---and that its arc is the classroom's reading from the centralized's server to the privacy's frontier.
Zen Revista, 10 IA· Zenodo (CERN European Organi...· 0 citations
Federated Learning (FL) offers a promising paradigm for decentralized machine learning, enabling collaborative model training without direct data sharing. However, traditional privacy-preserving techniques within FL often rely on ad-hoc assumptions and lack a rigorous theoretical basis. This work introduces an information-theoretic framework to address this limitation. We define a "Privacy Loss Function" predicated on mutual information between local models and global updates, providing a quantifiable measure of information leakage. The framework leverages established techniques such as differential privacy and homomorphic encryption to minimize this loss, ultimately leading to more robust and trustworthy FL systems. Our approach moves beyond intuitive notions of privacy, offering a mathematically sound foundation for designing and analyzing FL protocols, facilitating the development of truly secure and efficient distributed learning solutions. The core contribution is the formalization of privacy risk in FL using information-theoretic principles, enabling a more precise understanding and control over data leakage.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper presents a novel approach to collaborative scientific data analysis leveraging Decentralized Federated Learning with Differential Privacy (DFLDP). The core challenge in many scientific domains is the reluctance to share raw data due to stringent privacy regulations and intellectual property protections. Traditional Federated Learning (FL) solutions, while offering a degree of data privacy, still rely on centralized aggregation, a point of vulnerability. Our proposed DFLDP framework addresses this limitation by adopting a decentralized architecture where individual researchers maintain complete control over their datasets. Crucially, we integrate differential privacy mechanisms directly into the aggregation process, adding a quantifiable layer of protection against data leakage. This ensures that the learned model benefits from the collective knowledge of multiple researchers without revealing individual data contributions. The system utilizes a gossip-based communication protocol for model updates, minimizing communication overhead. We formally define the mathematical framework, outlining the key components and their interactions. The system's performance is evaluated in a simulated environment, demonstrating the effectiveness of the DFLDP approach in achieving accurate models while upholding stringent privacy guarantees. The core claim of this work is that sharing raw scientific data for federated learning is often prohibited due to privacy concerns and intellectual property restrictions. The core mechanism implemented is the realization of a federated learning system that utilizes differential privacy to protect data during aggregation, while also employing a decentralized architecture where individual researchers retain control over their data. This new approach combines federated learning with differential privacy and decentralization, enabling collaborative scientific discovery without compromising data privacy or intellectual property rights.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Knowledge graph embedding techniques have gained significant traction in representing complex relationships within knowledge graphs, enabling applications such as link prediction, entity recommendation, and semantic search. However, the training of these embeddings often relies on consolidating vast amounts of data from disparate sources, leading to substantial privacy risks. This paper proposes a novel approach to distributed knowledge graph embedding using federated learning, designed to mitigate these privacy concerns. We introduce a framework where multiple data sources independently train local knowledge graph embeddings. These local models are then aggregated using federated learning algorithms, resulting in a global knowledge graph embedding model without direct data sharing. The proposed method aims to balance embedding quality with robust privacy protection. We detail the technical aspects of the framework, including the selection of appropriate federated learning algorithms and strategies for addressing potential heterogeneity in data distributions. Experimental considerations and future research directions are also discussed.
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 data. However, the inherent collaborative nature of FL still poses privacy risks. This paper investigates the integration of differential privacy (DP) into the FL framework to provide an enhanced level of privacy protection. We introduce a novel approach where noise is injected into model parameters during the training process, adhering to the principles of DP. This mechanism mitigates the risk of information leakage from individual user data while maintaining model accuracy. We formally define the proposed algorithm and analyze its privacy-utility trade-off. The results demonstrate that the incorporation of DP significantly strengthens the privacy guarantees of FL, offering a robust solution for privacy-sensitive applications. Our work contributes to the growing body of research focused on secure and privacy-preserving FL techniques.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper presents a novel approach to distributed Bayesian inference that leverages the strengths of federated learning and differential privacy. The core idea is to execute Bayesian inference locally on a network of devices, aggregating updates while simultaneously protecting individual privacy. We introduce a framework where each device independently performs Bayesian inference on its local data and then adds noise to the updates based on differential privacy guarantees. This ensures that no single device's contribution can be identified, thus preserving privacy. The resulting system achieves accurate Bayesian inference across a decentralized network, offering a practical solution for privacy-sensitive data analysis. This work provides a new method for distributed learning which combines Bayesian inference, federated learning and differential privacy.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper proposes a novel approach to decentralized learning utilizing Federated Graph Neural Networks (FedGNNs). The core idea is to facilitate collaborative knowledge discovery across a network of devices by employing locally maintained graph representations and periodically synchronized Graph Neural Networks (GNNs). This framework addresses the limitations of traditional federated learning, particularly when dealing with graph-structured data, where raw data sharing poses significant privacy concerns. The system avoids direct data exchange by allowing devices to collaboratively learn through the exchange of model updates, preserving data privacy while enabling effective knowledge transfer. The proposed FedGNN architecture consists of local graphs and locally trained GNNs, synchronized via a novel aggregation mechanism. We demonstrate the feasibility and effectiveness of this approach through a theoretical analysis and outline the key components required for implementation. The system is designed to be scalable and adaptable to various decentralized network topologies. This work represents a significant step towards privacy-preserving collaborative learning in complex, graph-based environments.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
The reach of Internet of Things (IoT) devices in cross domain applications has recently resulted in a significant rise in the burden on wireless communication systems. The modern wireless communication systems are under stress due to fast deployment of the Internet of Things’ (IoT) in homes, businesses, and smart cities. It becomes more challenging to balance the bandwidth in these ultra-dense environments. Here many heterogeneous devices are involved and need a finite amount of radio spectrum. It becomes difficult for conventional spectrum assignment and sensing techniques to manage due to unpredictable traffic volumes, varying interference, and quickly changing channel conditions. Hence, there is the necessity for future systems to find a reactive mechanism and implement predictive strategies that can predict the changes in the spectrum in coming times. Machine learning has become a promising technology facilitator in this context. The predictive abilities of ML make it possible to have a smarter transmission scheduling, enhanced interference avoidance, and more effective use of limited spectrum resources. This chapter showcases a review and assessment of ML-based spectrum forecasting methods designed for dense IoT environments and setups. It reviews a wide range of learning techniques, like deep learning architectures, supervised and unsupervised methods, and reinforcement learning models, and discusses on how it can be deployed for significant tasks like channel occupancy prediction, interference mitigation, and enabling dynamic access decisions. This chapter also includes the review and assessment of emerging system architectures that can reduce latency, save device energy, and ensure privacy in distributed IoT networks, like edge-assisted and federated learning. The issues like how ML-enabled forecasting improves spectrum efficiency, reduces collision rates, and helps in maintaining quality of service (QoS) in large-scale IoT deployments through comparative analysis and case-driven discussion is also discussed in this chapter. The chapter finally summarizes new research directions that impacts the development of spectrum-intelligent IoT and 6G communication systems in future.
This paper presents a novel approach to distributed Bayesian inference that leverages the strengths of federated learning and differential privacy. The core idea is to execute Bayesian inference locally on a network of devices, aggregating updates while simultaneously protecting individual privacy. We introduce a framework where each device independently performs Bayesian inference on its local data and then adds noise to the updates based on differential privacy guarantees. This ensures that no single device's contribution can be identified, thus preserving privacy. The resulting system achieves accurate Bayesian inference across a decentralized network, offering a practical solution for privacy-sensitive data analysis. This work provides a new method for distributed learning which combines Bayesian inference, federated learning and differential privacy.
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.
