arXiv subjects

Luca Foschini

Publications and source records attributed to Luca Foschini.

17 recordsLinked to original sources

arXiv2026

Decentralized Stratified Sampling for Low-Latency Approximate Geospatial Data Stream Processing in Edge-Cloud Architectures

The exponential growth of geospatial data streams flowing from IoT devices challenges conventional cloud-based analytics, which typically suffer from network bandwidth waste and latency, basically attributed to the data being managed completely by Cloud, such as centralized sampling. To address this gap, we propose EdgeApproxGeo, a novel edge-cloud architecture that performs spatial-stratified online sampling at network edge devices near data sources. Our system introduces a novel sampling method called EdgeSOS, which is a unique decentralized, geohash-based stratified sampling algorithm designed to operate independently at resource-constrained edge nodes without cross-node synchronization, coupled with spatial-aware data distribution and topic routing in Apache Kafka data stream ingestion, aiming at optimizing downstream data stream processing analytics. We evaluated our system on two real-world geo-referenced datasets, mobility and air quality, and EdgeApproxGeo achieves a significant speedup over cloud-only baselines while maintaining errors in check (e.g., MAPE < 10% error rate at 80% sampling rate). We further demonstrate that coarser geohash granularity (e.g., Geohash-5) can reduce error figures by 30% as compared to finer counterparts (i.e., Geohash-6), thus revealing a tunable accuracy-efficiency trade-off. Our standard-compliant prototype, built atop Apache Kafka and Apache Spark, further validates the utility of edge-deployed approximate query processing for real-time big geospatial data analytics.

cs.DC↗

arXiv2026

MANATEE: A DevOps Platform for xApp Lifecycle Management and Testing in Open RAN

The shift to disaggregated 5G architectures introduces unprecedented flexibility but also significant complexity in Beyond 5G Radio Access Networks (RANs). Open RAN enables programmability through xApps, yet deploying and validating these applications is critical given the nature of the systems they aim to control. Current Open RAN ecosystems lack robust lifecycle management of xApps that enable automated testing, seamless migration, and production-grade observability, resulting in slow, error-prone xApp delivery. To address these issues, DevOps practices can streamline the xApp lifecycle by integrating Continuous Integration/Continuous Deployment (CI/CD) pipelines with advanced traffic management and monitoring, such as leveraging service mesh technologies to enable progressive deployment strategies (e.g., canary releases and A/B testing) to ensure fine-grained observability and resilience. The solution presented in this article, MANATEE (Mesh Architecture for Radio Access Network Automation and TEsting Ecosystems), is the first platform that combines these principles to simplify xApp delivery into production, accelerate innovation, and guarantee performance across heterogeneous O-RAN environments. We prototyped MANATEE on a Kubernetes cluster integrated with the O-RAN Software Community Near-Real Time RAN Intelligent Controller (RIC), as well as with service mesh technologies, to facilitate testing of xApps across simulated, emulated, and real testbed environments. Our experimental results demonstrate that service mesh integration introduces minimal overhead (below 1 ms latency), while enabling reliable canary deployments with fine-grained traffic control and conflict-free A/B testing through circuit-breaking mechanisms.

cs.NI↗

arXiv2025

A decentralized future for the open-science databases

Continuous and reliable access to curated biological data repositories is indispensable for accelerating rigorous scientific inquiry and fostering reproducible research. Centralized repositories, though widely used, are vulnerable to single points of failure arising from cyberattacks, technical faults, natural disasters, or funding and political uncertainties. This can lead to widespread data unavailability, data loss, integrity compromises, and substantial delays in critical research, ultimately impeding scientific progress. Centralizing essential scientific resources in a single geopolitical or institutional hub is inherently dangerous, as any disruption can paralyze diverse ongoing research. The rapid acceleration of data generation, combined with an increasingly volatile global landscape, necessitates a critical re-evaluation of the sustainability of centralized models. Implementing federated and decentralized architectures presents a compelling and future-oriented pathway to substantially strengthen the resilience of scientific data infrastructures, thereby mitigating vulnerabilities and ensuring the long-term integrity of data. Here, we examine the structural limitations of centralized repositories, evaluate federated and decentralized models, and propose a hybrid framework for resilient, FAIR, and sustainable scientific data stewardship. Such an approach offers a significant reduction in exposure to governance instability, infrastructural fragility, and funding volatility, and also fosters fairness and global accessibility. The future of open science depends on integrating these complementary approaches to establish a globally distributed, economically sustainable, and institutionally robust infrastructure that safeguards scientific data as a public good, further ensuring continued accessibility, interoperability, and preservation for generations to come.

cs.DB↗

arXiv2025

The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models

Background: Emerging reports of "AI psychosis" are on the rise, where user-LLM interactions may exacerbate or induce psychosis or adverse psychological symptoms. Whilst the sycophantic and agreeable nature of LLMs can be beneficial, it becomes a vector for harm by reinforcing delusional beliefs in vulnerable users. Methods: Psychosis-bench is a novel benchmark designed to systematically evaluate the psychogenicity of LLMs comprises 16 structured, 12-turn conversational scenarios simulating the progression of delusional themes(Erotic Delusions, Grandiose/Messianic Delusions, Referential Delusions) and potential harms. We evaluated eight prominent LLMs for Delusion Confirmation (DCS), Harm Enablement (HES), and Safety Intervention(SIS) across explicit and implicit conversational contexts. Findings: Across 1,536 simulated conversation turns, all LLMs demonstrated psychogenic potential, showing a strong tendency to perpetuate rather than challenge delusions (mean DCS of 0.91 $\pm$0.88). Models frequently enabled harmful user requests (mean HES of 0.69 $\pm$0.84) and offered safety interventions in only roughly a third of applicable turns (mean SIS of 0.37 $\pm$0.48). 51 / 128 (39.8%) of scenarios had no safety interventions offered. Performance was significantly worse in implicit scenarios, models were more likely to confirm delusions and enable harm while offering fewer interventions (p < .001). A strong correlation was found between DCS and HES (rs = .77). Model performance varied widely, indicating that safety is not an emergent property of scale alone. Conclusion: This study establishes LLM psychogenicity as a quantifiable risk and underscores the urgent need for re-thinking how we train LLMs. We frame this issue not merely as a technical challenge but as a public health imperative requiring collaboration between developers, policymakers, and healthcare professionals.

cs.LG↗

arXiv2025

FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks

Federated Learning (FL) can be vulnerable to attacks, such as model poisoning, where adversaries send malicious local weights to compromise the global model. Federated Unlearning (FU) is emerging as a solution to address such vulnerabilities by selectively removing the influence of detected malicious contributors on the global model without complete retraining. However, unlike typical FU scenarios where clients are trusted and cooperative, applying FU with malicious and possibly colluding clients is challenging because their collaboration in unlearning their data cannot be assumed. This work presents FedUP, a lightweight FU algorithm designed to efficiently mitigate malicious clients' influence by pruning specific connections within the attacked model. Our approach achieves efficiency by relying only on clients' weights from the last training round before unlearning to identify which connections to inhibit. Isolating malicious influence is non-trivial due to overlapping updates from benign and malicious clients. FedUP addresses this by carefully selecting and zeroing the highest magnitude weights that diverge the most between the latest updates from benign and malicious clients while preserving benign information. FedUP is evaluated under a strong adversarial threat model, where up to 50%-1 of the clients could be malicious and have full knowledge of the aggregation process. We demonstrate the effectiveness, robustness, and efficiency of our solution through experiments across IID and Non-IID data, under label-flipping and backdoor attacks, and by comparing it with state-of-the-art (SOTA) FU solutions. In all scenarios, FedUP reduces malicious influence, lowering accuracy on malicious data to match that of a model retrained from scratch while preserving performance on benign data. FedUP achieves effective unlearning while consistently being faster and saving storage compared to the SOTA.

cs.LG↗

arXiv2024

Croissant: A Metadata Format for ML-Ready Datasets

Data is a critical resource for machine learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that creates a shared representation across ML tools, frameworks, and platforms. Croissant makes datasets more discoverable, portable, and interoperable, thereby addressing significant challenges in ML data management. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, enabling easy loading into the most commonly-used ML frameworks, regardless of where the data is stored. Our initial evaluation by human raters shows that Croissant metadata is readable, understandable, complete, yet concise.

cs.LG↗

arXiv2023

Generative models for wearables data

Data scarcity is a common obstacle in medical research due to the high costs associated with data collection and the complexity of gaining access to and utilizing data. Synthesizing health data may provide an efficient and cost-effective solution to this shortage, enabling researchers to explore distributions and populations that are not represented in existing observations or difficult to access due to privacy considerations. To that end, we have developed a multi-task self-attention model that produces realistic wearable activity data. We examine the characteristics of the generated data and quantify its similarity to genuine samples with both quantitative and qualitative approaches.

cs.LG↗

arXiv2023

KuberneTSN: a Deterministic Overlay Network for Time-Sensitive Containerized Environments

The emerging paradigm of resource disaggregation enables the deployment of cloud-like services across a pool of physical and virtualized resources, interconnected using a network fabric. This design embodies several benefits in terms of resource efficiency and cost-effectiveness, service elasticity and adaptability, etc. Application domains benefiting from such a trend include cyber-physical systems (CPS), tactile internet, 5G networks and beyond, or mixed reality applications, all generally embodying heterogeneous Quality of Service (QoS) requirements. In this context, a key enabling factor to fully support those mixed-criticality scenarios will be the network and the system-level support for time-sensitive communication. Although a lot of work has been conducted on devising efficient orchestration and CPU scheduling strategies, the networking aspects of performance-critical components remain largely unstudied. Bridging this gap, we propose KuberneTSN, an original solution built on the Kubernetes platform, providing support for time-sensitive traffic to unmodified application binaries. We define an architecture for an accelerated and deterministic overlay network, which includes kernel-bypassing networking features as well as a novel userspace packet scheduler compliant with the Time-Sensitive Networking (TSN) standard. The solution is implemented as tsn-cni, a Kubernetes network plugin that can coexist alongside popular alternatives. To assess the validity of the approach, we conduct an experimental analysis on a real distributed testbed, demonstrating that KuberneTSN enables applications to easily meet deterministic deadlines, provides the same guarantees of bare-metal deployments, and outperforms overlay networks built using the Flannel plugin.

cs.NI↗

arXiv2022

A New Agent-Based Intelligent Network Architecture

The advent of 5G and the design of its architecture has become possible because of the previous individual scientific works and standardization efforts on cloud computing and network softwarization. Software-defined Networking and Network Function Virtualization started separately to find their convolution into 5G network architecture. Then, the ongoing design of the future beyond 5G (B5G) and 6G network architecture cannot overlook the pivotal inputs of different independent standardization efforts about autonomic networking, service-based communication systems, and multi-access edge computing. This article provides the design and the characteristics of an agent-based, softwarized, and intelligent architecture, which coherently condenses and merges the independent proposed architectural works by different standardization working groups and bodies. This novel work is a helpful means for the design and standardization process of the futureB5G and 6G network architecture.

cs.NI↗

arXiv2021

Self-supervision of wearable sensors time-series data for influenza detection

Self-supervision may boost model performance in downstream tasks. However, there is no principled way of selecting the self-supervised objectives that yield the most adaptable models. Here, we study this problem on daily time-series data generated from wearable sensors used to detect onset of influenza-like illness (ILI). We first show that using self-supervised learning to predict next-day time-series values allows us to learn rich representations which can be adapted to perform accurate ILI prediction. Second, we perform an empirical analysis of three different self-supervised objectives to assess their adaptability to ILI prediction. Our results show that predicting the next day's resting heart rate or time-in-bed during sleep provides better representations for ILI prediction. These findings add to previous work demonstrating the practical application of self-supervised learning from activity data to improve health predictions.

cs.LG↗

arXiv2021

Towards Industrial Private AI: A two-tier framework for data and model security

With the advances in 5G and IoT devices, the industries are vastly adopting artificial intelligence (AI) techniques for improving classification and prediction-based services. However, the use of AI also raises concerns regarding privacy and security that can be misused or leaked. Private AI was recently coined to address the data security issue by combining AI with encryption techniques, but existing studies have shown that model inversion attacks can be used to reverse engineer the images from model parameters. In this regard, we propose a Federated Learning and Encryption-based Private (FLEP) AI framework that provides two-tier security for data and model parameters in an IIoT environment. We proposed a three-layer encryption method for data security and provide a hypothetical method to secure the model parameters. Experimental results show that the proposed method achieves better encryption quality at the expense of slightly increased execution time. We also highlight several open issues and challenges regarding the FLEP AI framework's realization.

cs.CR↗

arXiv2019

Reproducibility in Machine Learning for Health

Machine learning algorithms designed to characterize, monitor, and intervene on human health (ML4H) are expected to perform safely and reliably when operating at scale, potentially outside strict human supervision. This requirement warrants a stricter attention to issues of reproducibility than other fields of machine learning. In this work, we conduct a systematic evaluation of over 100 recently published ML4H research papers along several dimensions related to reproducibility. We find that the field of ML4H compares poorly to more established machine learning fields, particularly concerning data and code accessibility. Finally, drawing from success in other fields of science, we propose recommendations to data providers, academic publishers, and the ML4H research community in order to promote reproducible research moving forward.

cs.LG↗

arXiv2019

Adversarial Examples for Electrocardiograms

In recent years, the electrocardiogram (ECG) has seen a large diffusion in both medical and commercial applications, fueled by the rise of single-lead versions. Single-lead ECG can be embedded in medical devices and wearable products such as the injectable Medtronic Linq monitor, the iRhythm Ziopatch wearable monitor, and the Apple Watch Series 4. Recently, deep neural networks have been used to automatically analyze ECG tracings, outperforming even physicians specialized in cardiac electrophysiology in detecting certain rhythm irregularities. However, deep learning classifiers have been shown to be brittle to adversarial examples, which are examples created to look incontrovertibly belonging to a certain class to a human eye but contain subtle features that fool the classifier into misclassifying them into the wrong class. Very recently, adversarial examples have also been created for medical-related tasks. Yet, traditional attack methods to create adversarial examples, such as projected gradient descent (PGD) do not extend directly to ECG signals, as they generate examples that introduce square wave artifacts that are not physiologically plausible. Here, we developed a method to construct smoothed adversarial examples for single-lead ECG. First, we implemented a neural network model achieving state-of-the-art performance on the data from the 2017 PhysioNet/Computing-in-Cardiology Challenge for arrhythmia detection from single lead ECG classification. For this model, we utilized a new technique to generate smoothed examples to produce signals that are 1) indistinguishable to cardiologists from the original examples and 2) incorrectly classified by the neural network. Finally, we show that adversarial examples are not unique and provide a general technique to collate and perturb known adversarial examples to create new ones.

eess.SP↗

arXiv2018

Learning Individualized Cardiovascular Responses from Large-scale Wearable Sensors Data

We consider the problem of modeling cardiovascular responses to physical activity and sleep changes captured by wearable sensors in free living conditions. We use an attentional convolutional neural network to learn parsimonious signatures of individual cardiovascular response from data recorded at the minute level resolution over several months on a cohort of 80k people. We demonstrate internal validity by showing that signatures generated on an individual's 2017 data generalize to predict minute-level heart rate from physical activity and sleep for the same individual in 2018, outperforming several time-series forecasting baselines. We also show external validity demonstrating that signatures outperform plain resting heart rate (RHR) in predicting variables associated with cardiovascular functions, such as age and Body Mass Index (BMI). We believe that the computed cardiovascular signatures have utility in monitoring cardiovascular health over time, including detecting abnormalities and quantifying recovery from acute events.

cs.LG↗

arXiv2018

Spatial Coherence of Oriented White Matter Microstructure: Applications to White Matter Regions Associated with Genetic Similarity

We present a method to discover differences between populations with respect to the spatial coherence of their oriented white matter microstructure in arbitrarily shaped white matter regions. This method is applied to diffusion MRI scans of a subset of the Human Connectome Project dataset: 57 pairs of monozygotic and 52 pairs of dizygotic twins. After controlling for morphological similarity between twins, we identify 3.7% of all white matter as being associated with genetic similarity (35.1k voxels, $p < 10^{-4}$, false discovery rate 1.5%), 75% of which spatially clusters into twenty-two contiguous white matter regions. Furthermore, we show that the orientation similarity within these regions generalizes to a subset of 47 pairs of non-twin siblings, and show that these siblings are on average as similar as dizygotic twins. The regions are located in deep white matter including the superior longitudinal fasciculus, the optic radiations, the middle cerebellar peduncle, the corticospinal tract, and within the anterior temporal lobe, as well as the cerebellum, brain stem, and amygdalae. These results extend previous work using undirected fractional anisotrophy for measuring putative heritable influences in white matter. Our multidirectional extension better accounts for crossing fiber connections within voxels. This bottom up approach has at its basis a novel measurement of coherence within neighboring voxel dyads between subjects, and avoids some of the fundamental ambiguities encountered with tractographic approaches to white matter analysis that estimate global connectivity.

stat.AP↗

arXiv2016

Intra-day Activity Better Predicts Chronic Conditions

In this work we investigate intra-day patterns of activity on a population of 7,261 users of mobile health wearable devices and apps. We show that: (1) using intra-day step and sleep data recorded from passive trackers significantly improves classification performance on self-reported chronic conditions related to mental health and nervous system disorders, (2) Convolutional Neural Networks achieve top classification performance vs. baseline models when trained directly on multivariate time series of activity data, and (3) jointly predicting all condition classes via multi-task learning can be leveraged to extract features that generalize across data sets and achieve the highest classification performance.

stat.ML↗

arXiv2009

Untangling the Braid: Finding Outliers in a Set of Streams

Monitoring the performance of large shared computing systems such as the cloud computing infrastructure raises many challenging algorithmic problems. One common problem is to track users with the largest deviation from the norm (outliers), for some measure of performance. Taking a stream-computing perspective, we can think of each user's performance profile as a stream of numbers (such as response times), and the aggregate performance profile of the shared infrastructure as a "braid" of these intermixed streams. The monitoring system's goal then is to untangle this braid sufficiently to track the top k outliers. This paper investigates the space complexity of one-pass algorithms for approximating outliers of this kind, proves lower bounds using multi-party communication complexity, and proposes small-memory heuristic algorithms. On one hand, stream outliers are easily tracked for simple measures, such as max or min, but our theoretical results rule out even good approximations for most of the natural measures such as average, median, or the quantiles. On the other hand, we show through simulation that our proposed heuristics perform quite well for a variety of synthetic data.

cs.DB↗