arXiv subjects

Andrea Vitaletti

Publications and source records attributed to Andrea Vitaletti.

At least 19 recordsLinked to original sources

arXiv2026

GuidaPA: Privacy-Preserving Chatbot for Public Administration via Federated Learning

We present GuidaPA, a privacy-preserving chatbot for the Italian Public Administration (PA) trained via Federated Learning (FL) on documentation from two national PA platforms, SIGESON and SIDFORS. Our corpus includes approximately 8 pages of SIGESON manuals and 31 pages of SIDFORS manuals/FAQs; while this study uses public documentation as a safe proxy, the intended deployment extends to restricted internal sources (e.g., tickets, officer manuals, database extracts) that can not be centrally pooled due to regulatory and organizational constraints. GuidaPA integrates role-based access control, secure client-side preprocessing, explicit monitoring of non-IID effects, and parameter-efficient federated fine-tuning of large language models. Using QLoRA (4-bit) over 15 federated rounds with an 80/20 train-test split per client, we evaluate answer quality with ROUGE, BLEU-4, and METEOR. The best federated model achieves ROUGE-1/2/L of 61.10/55.77/59.44, BLEU-4 of 45.02, and METEOR of 63.94-close to private centralized fine-tuning while keeping data on-site. Compared to the general-purpose baseline, domain fine-tuning improves ROUGE-1 from 41.45 to 62.18 and BLEU-4 from 26.97 to 50.90. Overall, the results indicate that FL can deliver high-quality conversational AI for public services without centralized data sharing

cs.AI↗

arXiv2026

FedLECC: Cluster- and Loss-Guided Client Selection for Federated Learning under Non-IID Data

Federated Learning (FL) enables distributed Artificial Intelligence (AI) across cloud-edge environments by allowing collaborative model training without centralizing data. In cross-device deployments, FL systems face strict communication and participation constraints, as well as strong non-independent and identically distributed (non-IID) data that degrades convergence and model quality. Since only a subset of devices (a.k.a clients) can participate per training round, intelligent client selection becomes a key systems challenge. This paper proposes FedLECC (Federated Learning with Enhanced Cluster Choice), a lightweight, cluster-aware, and loss-guided client selection strategy for cross-device FL. FedLECC groups clients by label-distribution similarity and prioritizes clusters and clients with higher local loss, enabling the selection of a small yet informative and diverse set of clients. Experimental results under severe label skew show that FedLECC improves test accuracy by up to 12%, while reducing communication rounds by approximately 22% and overall communication overhead by up to 50% compared to strong baselines. These results demonstrate that informed client selection improves the efficiency and scalability of FL workloads in cloud-edge systems.

cs.DC↗

arXiv2026

Clust-PSI-PFL: A Population Stability Index Approach for Clustered Non-IID Personalized Federated Learning

Federated learning (FL) supports privacy-preserving, decentralized machine learning (ML) model training by keeping data on client devices. However, non-independent and identically distributed (non-IID) data across clients biases updates and degrades performance. To alleviate these issues, we propose Clust-PSI-PFL, a clustering-based personalized FL framework that uses the Population Stability Index (PSI) to quantify the level of non-IID data. We compute a weighted PSI metric, $WPSI^L$, which we show to be more informative than common non-IID metrics (Hellinger, Jensen-Shannon, and Earth Mover's distance). Using PSI features, we form distributionally homogeneous groups of clients via K-means++; the number of optimal clusters is chosen by a systematic silhouette-based procedure, typically yielding few clusters with modest overhead. Across six datasets (tabular, image, and text modalities), two partition protocols (Dirichlet with parameter $α$ and Similarity with parameter S), and multiple client sizes, Clust-PSI-PFL delivers up to 18% higher global accuracy than state-of-the-art baselines and markedly improves client fairness by a relative improvement of 37% under severe non-IID data. These results establish PSI-guided clustering as a principled, lightweight mechanism for robust PFL under label skew.

cs.LG↗

arXiv2026

A Proof of Concept for a Digital Twin of an Ultrasonic Fermentation System

This paper presents the design and implementation of a proof of concept digital twin for an innovative ultrasonic-enhanced beer-fermentation system, developed to enable intelligent monitoring, prediction, and actuation in yeast-growth environments. A traditional fermentation tank is equipped with a piezoelectric transducer able to irradiate the tank with ultrasonic waves, providing an external abiotic stimulus to enhance the growth of yeast and accelerate the fermentation process. At its core, the digital twin incorporates a predictive model that estimates yeast's culture density over time based on the surrounding environmental conditions. To this end, we implement, tailor and extend the model proposed in Palacios et al., allowing us to effectively handle the limited number of available training samples by using temperature, ultrasonic frequency, and duty cycle as inputs. The results obtained along with the assessment of model performance demonstrate the feasibility of the proposed approach.

cs.ET↗

arXiv2025

Decentralized Fair Exchange with Advertising

Before a fair exchange takes place, there is typically an advertisement phase with the goal of increasing the appeal of possessing a digital asset while keeping it sufficiently hidden. Advertisement phases are implicit in mainstream definitions, and therefore are not explicitly integrated within fair-exchange protocols. In this work we give an explicit definition for such a fair exchange in a setting where parties communicate via broadcast messages only (i.e., no point-to-point connection between seller and buyer is needed). Next, we construct a fair-exchange protocol satisfying our new definition using zk-SNARKs and relying on mainstream decentralized platforms (i.e., a blockchain with smart contracts like Ethereum and a decentralized storage system like IPFS). Experimental results confirm the practical relevance of our decentralized approach, paving the road towards building decentralized marketplaces where users can, even anonymously, and without direct off-chain communications, effectively advertise and exchange their digital assets as part of a system of enhanced NFTs.

cs.CR↗

arXiv2025

On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions

Federated Learning (FL) is an emerging distributed machine learning paradigm enabling multiple clients to train a global model collaboratively without sharing their raw data. While FL enhances data privacy by design, it remains vulnerable to various security and privacy threats. This survey provides a comprehensive overview of more than 200 papers regarding the state-of-the-art attacks and defense mechanisms developed to address these challenges, categorizing them into security-enhancing and privacy-preserving techniques. Security-enhancing methods aim to improve FL robustness against malicious behaviors such as byzantine attacks, poisoning, and Sybil attacks. At the same time, privacy-preserving techniques focus on protecting sensitive data through cryptographic approaches, differential privacy, and secure aggregation. We critically analyze the strengths and limitations of existing methods, highlight the trade-offs between privacy, security, and model performance, and discuss the implications of non-IID data distributions on the effectiveness of these defenses. Furthermore, we identify open research challenges and future directions, including the need for scalable, adaptive, and energy-efficient solutions operating in dynamic and heterogeneous FL environments. Our survey aims to guide researchers and practitioners in developing robust and privacy-preserving FL systems, fostering advancements safeguarding collaborative learning frameworks' integrity and confidentiality.

cs.CR↗

arXiv2025

A Thorough Assessment of the Non-IID Data Impact in Federated Learning

Federated learning (FL) allows collaborative machine learning (ML) model training among decentralized clients' information, ensuring data privacy. The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data. This open problem has notable consequences, such as decreased model performance and more significant convergence times. Despite its importance, experimental studies systematically addressing all types of data heterogeneity (a.k.a. non-IIDness) remain scarce. We aim to fill this gap by assessing and quantifying the non-IID effect through a thorough empirical analysis. We use the Hellinger Distance (HD) to measure differences in distribution among clients. Our study benchmarks four state-of-the-art strategies for handling non-IID data, including label, feature, quantity, and spatiotemporal skewness, under realistic and controlled conditions. This is the first comprehensive analysis of the spatiotemporal skew effect in FL. Our findings highlight the significant impact of label and spatiotemporal skew non-IID types on FL model performance, with notable performance drops occurring at specific HD thresholds. Additionally, the FL performance is heavily affected mainly when the non-IIDness is extreme. Thus, we provide recommendations for FL research to tackle data heterogeneity effectively. Our work represents the most extensive examination of non-IIDness in FL, offering a robust foundation for future research.

cs.LG↗

arXiv2025

Share a Tiny Space of Your Freezer to Increase Resilience of Ex-situ Seed Conservation

More than 95% of the crop genetic erosion articles analyzed in [9] reported changes in diversity, with nearly 80% providing evidence of loss. The lack of diversity presents a severe risk to the security of global food systems. Without seed diversity, it is difficult for plants to adapt to pests, diseases, and changing climate conditions. Genebanks, such as the Svalbard Global Seed Vault, are valuable initiatives to preserve seed diversity in a single secure and safe place. However, according to our analysis of the data available in the Seed Portal, the redundancy for some species might be limited, posing a potential threat to their future availability. Interestingly, the conditions to properly store seeds in genebanks, are the ones available in the freezers of our homes. This paper lays out a vision for Distributed Seed Storage relying on a peer-to-peer infrastructure of domestic freezers to increase the overall availability of seeds. We present a Proof-of-Concept focused on monitoring the proper seed storing conditions and incentive user participation through a Blockchain lottery. The PoC proves the feasibility of the proposed approach and outlines the main technical issues that still need to be efficiently solved to realize a fully-fledged solution.

cs.DC↗

arXiv2025

Efficient Query Verification for Blockchain Superlight Clients Using SNARKs

Blockchains are among the most powerful technologies to realize decentralized information systems. In order to safely enjoy all guarantees provided by a blockchain, one should maintain a full node, therefore maintaining an updated local copy of the ledger. This allows one to locally verify transactions, states of smart contracts, and to compute any information over them. Unfortunately, for obvious practical reasons, a very large part of blockchain-based information systems consists of users relying on clients that access data stored in blockchains only through servers, without verifying what is received. In notable use cases, the user has application-specific queries that can be answered only by very few servers, sometimes all belonging to the same organization. This clearly re-introduces a single point of failure. In this work we present an architecture allowing superlight clients (i.e., clients that do not want to download the involved transactions) to outsource the computation of a query to a (possibly untrusted) server, receiving a trustworthy answer. Our architecture relies on the power of SNARKs and makes them lighter to compute by using data obtained from full nodes and blockchain explorers, possibly leveraging the existence of smart contracts. The viability of our architecture is confirmed by an experimental evaluation on concrete scenarios. Our work paves the road towards blockchain-based information systems that remain decentralized and reliable even when users rely on common superlight clients (e.g., smartphones).

cs.CR↗

arXiv2024

Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions

Recent advances in machine learning have highlighted Federated Learning (FL) as a promising approach that enables multiple distributed users (so-called clients) to collectively train ML models without sharing their private data. While this privacy-preserving method shows potential, it struggles when data across clients is not independent and identically distributed (non-IID) data. The latter remains an unsolved challenge that can result in poorer model performance and slower training times. Despite the significance of non-IID data in FL, there is a lack of consensus among researchers about its classification and quantification. This technical survey aims to fill that gap by providing a detailed taxonomy for non-IID data, partition protocols, and metrics to quantify data heterogeneity. Additionally, we describe popular solutions to address non-IID data and standardized frameworks employed in FL with heterogeneous data. Based on our state-of-the-art survey, we present key lessons learned and suggest promising future research directions.

cs.LG↗

arXiv2024

Predicting Award Winning Research Papers at Publication Time

In recent years, many studies have been focusing on predicting the scientific impact of research papers. Most of these predictions are based on citations count or rely on features obtainable only from already published papers. In this study, we predict the likelihood for a research paper of winning an award only relying on information available at publication time. For each paper, we build the citation subgraph induced from its bibliography. We initially consider some features of this subgraph, such as the density and the global clustering coefficient, to make our prediction. Then, we mix this information with textual features, extracted from the abstract and the title, to obtain a more accurate final prediction. We made our experiments considering the ArnetMiner citation graph, while the ground truth on award-winning papers has been obtained from a collection of best paper awards from 32 computer science conferences. In our experiment, we obtained an encouraging F1 score of 0.694. Remarkably, The high recall and the low false negatives rate, show how the model performs very well at identifying papers that will not win an award. This behavior can help researchers in getting a first evaluation of their work at publication time. Lastly, we made some first experiments on interpretability. Our results highlight some interesting patterns both in topological and textual features.

cs.IR↗

arXiv2024

Application of federated learning techniques for arrhythmia classification using 12-lead ECG signals

Artificial Intelligence-based (AI) analysis of large, curated medical datasets is promising for providing early detection, faster diagnosis, and more effective treatment using low-power Electrocardiography (ECG) monitoring devices information. However, accessing sensitive medical data from diverse sources is highly restricted since improper use, unsafe storage, or data leakage could violate a person's privacy. This work uses a Federated Learning (FL) privacy-preserving methodology to train AI models over heterogeneous sets of high-definition ECG from 12-lead sensor arrays collected from six heterogeneous sources. We evaluated the capacity of the resulting models to achieve equivalent performance compared to state-of-the-art models trained in a Centralized Learning (CL) fashion. Moreover, we assessed the performance of our solution over Independent and Identical distributed (IID) and non-IID federated data. Our methodology involves machine learning techniques based on Deep Neural Networks and Long-Short-Term Memory models. It has a robust data preprocessing pipeline with feature engineering, selection, and data balancing techniques. Our AI models demonstrated comparable performance to models trained using CL, IID, and non-IID approaches. They showcased advantages in reduced complexity and faster training time, making them well-suited for cloud-edge architectures.

cs.LG↗

arXiv2021

Empowering Citizens by a Blockchain-Based Robinson List

A Robinson list protects phone subscribers against commercial spam calls. Its least basic functionality is to collect the denial of the subscribers to be contacted by market operators. Nowadays, Robinson lists run as centralised services, which implies that citizens should trust third parties for the management of their choices. In this paper, we show a design that allows us to realise a Robinson list as a decentralised service. Our work leverages the experience developed by Fondazione Ugo Bordoni as the manager of the Italian Robinson list. We present a general solution and a proof-of-concept (PoC) adopting the Algorand technology. We evaluate the performances of our PoC in terms of its scalability and of the latency perceived by the involved actors. We also discuss aspects related to identity management and privacy.

cs.CR↗

arXiv2020

Binding of Endpoints to Identifiers by On-Chain Proofs

In many applications, identity management (IdM) is used to associate a subject public key with an endpoint at which the subject can be contacted (telephone number, email, etc.). In decentralized applications based on distributed ledger technologies (DLTes), it is desirable for the IdM to be decentralized as well. Currently, endpoints are either verified by who needs it, which is impractical in DLT-based applications, or by a centralized authority, which contrasts with the spirit of DLTes. In this paper, we show two DLT-based protocols to prove the association between a subject and an endpoint in a decentralized manner, contributing in filling the gap of the current IdM approaches with respect to decentralization. Our protocols are compatible with a wide variety of endpoints. We analyze the security of our protocols and evaluate their performance and cost against the common approaches.

cs.DC↗

arXiv2019

Scenarios for Educational and Game Activities using Internet of Things Data

Raising awareness among young people and changing their behavior and habits concerning energy usage and the environment is key to achieving a sustainable planet. The goal to address the global climate problem requires informing the population on their roles in mitigation actions and adaptation of sustainable behaviors. Addressing climate change and achieve ambitious energy and climate targets requires a change in citizen behavior and consumption practices. IoT sensing and related scenario and practices, which address school children via discovery, gamification, and educational activities, are examined in this paper. Use of seawater sensors in STEM education, that has not previously been addressed, is included in these educational scenaria.

cs.HC↗

arXiv2017

Comparison of Decision Tree Based Classification Strategies to Detect External Chemical Stimuli from Raw and Filtered Plant Electrical Response

Plants monitor their surrounding environment and control their physiological functions by producing an electrical response. We recorded electrical signals from different plants by exposing them to Sodium Chloride (NaCl), Ozone (O3) and Sulfuric Acid (H2SO4) under laboratory conditions. After applying pre-processing techniques such as filtering and drift removal, we extracted few statistical features from the acquired plant electrical signals. Using these features, combined with different classification algorithms, we used a decision tree based multi-class classification strategy to identify the three different external chemical stimuli. We here present our exploration to obtain the optimum set of ranked feature and classifier combination that can separate a particular chemical stimulus from the incoming stream of plant electrical signals. The paper also reports an exhaustive comparison of similar feature based classification using the filtered and the raw plant signals, containing the high frequency stochastic part and also the low frequency trends present in it, as two different cases for feature extraction. The work, presented in this paper opens up new possibilities for using plant electrical signals to monitor and detect other environmental stimuli apart from NaCl, O3 and H2SO4 in future.

physics.bio-ph↗

arXiv2016

Drift Removal in Plant Electrical Signals via IIR Filtering Using Wavelet Energy

Plant electrical signals often contains low frequency drifts with or without the application of external stimuli. Quantification of the randomness in plant signals in a stimulus-specific way is hindered because the knowledge of vital frequency information in the actual biological response is not known yet. Here we design an optimum Infinite Impulse Response (IIR) filter which removes the low frequency drifts and preserves the frequency spectrum corresponding to the random component of the unstimulated plant signals by bringing the bias due to unknown artifacts and drifts to a minimum. We use energy criteria of wavelet packet transform (WPT) for optimization based tuning of the IIR filter parameters. Such an optimum filter enforces that the energy distribution of the pre-stimulus parts in different experiments are almost overlapped but under different stimuli the distributions of the energy get changed. The reported research may popularize plant signal processing, as a separate field, besides other conventional bioelectrical signal processing paradigms.

stat.AP↗

arXiv2016

Exploring Strategies for Classification of External Stimuli Using Statistical Features of the Plant Electrical Response

Plants sense their environment by producing electrical signals which in essence represent changes in underlying physiological processes. These electrical signals, when monitored, show both stochastic and deterministic dynamics. In this paper, we compute 11 statistical features from the raw non-stationary plant electrical signal time series to classify the stimulus applied (causing the electrical signal). By using different discriminant analysis based classification techniques, we successfully establish that there is enough information in the raw electrical signal to classify the stimuli. In the process, we also propose two standard features which consistently give good classification results for three types of stimuli - Sodium Chloride (NaCl), Sulphuric Acid (H2SO4) and Ozone (O3). This may facilitate reduction in the complexity involved in computing all the features for online classification of similar external stimuli in future.

physics.bio-ph↗