DFDario Fenoglio

Dario Fenoglio

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dario Fenoglio has a total of 25 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Security and Privacy in Federated Learning: A Survey and Unified Taxonomy of Threat Models, Attacks, and Defenses

    by Dario Fenoglio, Martin Gjoreski, Edoardo Gabrielli, Marc Langheinrich

    Federated Learning (FL) enables collaborative training across distributed data sources while preserving privacy by design. However, recent studies reveal that FL remains vulnerable to a broad spectrum of security and privacy threats, undermining its foundational promises. This survey presents a unified and comprehensive analysis of the FL threat landscape, critically examining adversarial strategies and their corresponding defenses. We propose a formal taxonomy that connects threat models to both security and privacy attacks and defenses to expose the relationships between attacker assumptions, attack strategies, and applicable defenses. We analyze state-of-the-art security attacks, including poisoning and resource exhaustion, and privacy attacks such as membership and data inference, highlighting their mechanisms and feasibility under realistic assumptions. We then review defense approaches spanning hardware-based solutions, cryptography, robust aggregation, perturbation, and training configurations, identifying key trade-offs, conflicts, limitations, and deployment guidelines. By jointly analyzing security and privacy attacks and defenses, we reveal shared vulnerabilities and opportunities for hybrid solutions. We conclude by outlining open challenges and promising directions for building robust and privacy-preserving FL systems in real-world deployments. This survey bridges theoretical guarantees with practical constraints to support the development of resilient FL pipelines.

  • Open Access

    ERIS: Enhancing Privacy and Communication Efficiency in Serverless Federated Learning

    by Dario Fenoglio, Pasquale Polverino, Jacopo Quizi, Martin Gjoreski, Marc Langheinrich

    Scaling federated learning (FL) to billion-parameter models introduces critical trade-offs between communication efficiency, model accuracy, and privacy guarantees. Existing solutions often tackle these challenges in isolation, sacrificing accuracy or relying on costly cryptographic tools. We propose ERIS, a serverless FL framework that balances privacy and accuracy while eliminating the server bottleneck and distributing the communication load. ERIS combines a model partitioning strategy, distributing aggregation across multiple client-side aggregators, with a distributed shifted gradient compression mechanism. We theoretically prove that ERIS (i) converges at the same rate as FedAvg under standard assumptions, and (ii) bounds mutual information leakage inversely with the number of aggregators, enabling strong privacy guarantees with no accuracy degradation. Experiments across image and text tasks, including large language models, confirm that ERIS achieves FedAvg-level accuracy while substantially reducing communication cost and improving robustness to membership inference and reconstruction attacks, without relying on heavy cryptography or noise injection.

  • Open Access

    Federated Concept-Based Models: Interpretable models with distributed supervision

    by Dario Fenoglio, Arianna Casanova, Francesco De Santis, Mohan Li, Gabriele Dominici, Johannes Schneider, Martin Gjoreski, Marc Langheinrich, Pietro Barbiero, Giovanni De Felice

    Concept-based models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept annotations are expensive to obtain and rarely available at scale within a single data source. Federated learning (FL) could alleviate this limitation by enabling cross-institutional training that leverages concept annotations distributed across multiple data owners. Yet, FL lacks interpretable modeling paradigms. Integrating CMs with FL is non-trivial: CMs assume a fixed concept space and a predefined model architecture, whereas real-world FL is heterogeneous and non-stationary, with institutions joining over time and bringing new supervision. In this work, we propose Federated Concept-based Models (F-CMs), a new methodology for deploying CMs in evolving FL settings. F-CMs aggregate concept-level information across institutions and efficiently adapt the model architecture in response to changes in the available concept supervision, while preserving institutional privacy. Empirically, F-CMs preserve the accuracy and intervention effectiveness of training settings with full concept supervision, while outperforming non-adaptive federated baselines. Notably, F-CMs enable interpretable inference on concepts not available to a given institution, a key novelty with respect to existing approaches.

  • Open Access

    Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors

    by Dario Fenoglio, Mohan Li, Davide Casnici, Matias Laporte, Shkurta Gashi, Silvia Santini, Martin Gjoreski, Marc Langheinrich

    Human Activity Recognition (HAR) benefits various application domains, including health and elderly care. Traditional HAR involves constructing pipelines reliant on centralized user data, which can pose privacy concerns as they necessitate the uploading of user data to a centralized server. This work proposes multi-frequency Federated Learning (FL) to enable: (1) privacy-aware ML; (2) joint ML model learning across devices with varying sampling frequency. We focus on head-worn devices (e.g., earbuds and smart glasses), a relatively unexplored domain compared to traditional smartwatch- or smartphone-based HAR. Results have shown improvements on two datasets against frequency-specific approaches, indicating a promising future in the multi-frequency FL-HAR task. The proposed network's implementation is publicly available for further research and development.

  • Open Access

    FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts

    by Dario Fenoglio, Mohan Li, Pietro Barbiero, Nicholas D. Lane, Marc Langheinrich, Martin Gjoreski

    Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy. Traditional FL methods often use a global model to fit all clients, assuming that clients' data are independent and identically distributed (IID). However, when this assumption does not hold, the global model accuracy may drop significantly, limiting FL applicability in real-world scenarios. To address this gap, we propose FLUX, a novel clustering-based FL (CFL) framework that addresses the four most common types of distribution shifts during both training and test time. To this end, FLUX leverages privacy-preserving client-side descriptor extraction and unsupervised clustering to ensure robust performance and scalability across varying levels and types of distribution shifts. Unlike existing CFL methods addressing non-IID client distribution shifts, FLUX i) does not require any prior knowledge of the types of distribution shifts or the number of client clusters, and ii) supports test-time adaptation, enabling unseen and unlabeled clients to benefit from the most suitable cluster-specific models. Extensive experiments across four standard benchmarks, two real-world datasets and ten state-of-the-art baselines show that FLUX improves performance and stability under diverse distribution shifts, achieving an average accuracy gain of up to 23 percentage points over the best-performing baselines, while maintaining computational and communication overhead comparable to FedAvg.

  • Open Access

    Federated Learning for Privacy-aware Cognitive Workload Estimation

    by Dario Fenoglio, Daniel Josifovski, Alessandro Gobbetti, Mattias Formo, Hristijan Gjoreski, Martin Gjoreski, Marc Langheinrich

    Human physiological monitoring has become easily accessible by integrating wearable devices into our lives, providing valuable real-time data. Methods for Cognitive Workload (CW) estimation utilize such physiological data to quantify CW during task execution. These methods are crucial for various domains, including mobile healthcare, forecasting human errors, and human-machine interaction. However, accurately estimating CW continues to pose a challenge due to the absence of objective ground truth data, context dependency, and the privacy sensitivity of the data. This study tackled the complex task of estimating CW based on privacy-sensitive data (e.g., eye movement, pupil diameter, blink information, and other physiological signals) using Federated Learning (FL) methods to improve user privacy. We compared the outcomes of the FL models with the more conventional centralized approach on two publicly-available datasets COLET and ADABase, which include data from 75 participants overall. The results highlight the efficacy of FL in collaboratively training a global (person-independent) model. The FL models achieved performances on par with centralized state-of-the-art models while preserving data privacy. Recognizing the importance of privacy in user sensing, FL presents a promising approach that enables wearable sensing applications in privacy-sensitive domains.


  • Open Access

    A Federated Unsupervised Personalisation for Cognitive Workload Estimation

    by Dario Fenoglio, Martin Gjoreski, Marc Langheinrich

    Accurate Cognitive Workload (CW) estimation, crucial in mobile healthcare and human-machine interaction, is impeded by client heterogeneity, data limitations, and privacy concerns, especially in the presence of Out-of-Distribution (OoD) clients. This study proposes a robust framework that is based on Federated Learning to protect data privacy, and utilizes context-based STRNet to enable joint cross-user learning on heterogeneous datasets, enhancing model generalisability. The framework includes a novel Unsupervised Client Personalisation strategy that prevents accuracy loss in OoD clients. We tested our framework on two publicly available CW datasets, COLET and ADABase. The framework improved the accuracy of centralized approaches while preserving data privacy. The framework is model-agnostic, efficient, and enables unsupervised personalisation for each client, bolstering the quality and robustness of the end-to-end deep learning models.