Alessio Orsino

Dr. Alessio Orsino

Department of Computer Science, Modeling, Electronics and Systems Engineering (DIMES), University of Calabria, Rende, Italy
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 April 2023 in IEEE Access
Verified
Journal Article
Open access
Loris BelcastroLoris Belcastro
Loris Belcastro
Fabrizio MarozzoFabrizio Marozzo
Fabrizio Marozzo
AOAlessio Orsino
Alessio Orsino
Domenico TaliaDomenico Talia
Domenico Talia
Paolo TrunfioPaolo Trunfio
Paolo Trunfio
In recent years, there has been an increase in the use of edge-cloud continuum solutions to efficiently collect and analyze data generated by IoT devices. In this paper, we investigate to what extent these solutions can manage tasks related to urban mobility, by combining real-time and low latency analysis offered by the edge with large computing and storage resources provided by the cloud. Our proposal is organized into three parts. The first part focuses on defining three application scenarios in which geotagged data generated by IoT objects, such as taxis, cars, and smartphones, are collected and analyzed through machine learning algorithms (i.e., next location prediction, location-based advertising, and points of interest recommendation). The second part is dedicated to modeling an edge-cloud continuum architecture capable of managing a large number of IoT devices and executing machine learning algorithms to analyze the data they generate. The third part analyzes the experimental results in which different design choices were evaluated, such as the number of devices and orchestration policies, to improve the performance of machine learning algorithms in terms of processing time, network delay, task failure, and computational resource utilization. The results highlight the potential benefits of edge and cloud cooperation in the three application scenarios, demonstrating that it significantly improves resource utilization and reduces the task failure rate compared to other widely adopted architectures, such as edge- or cloud-only architectures.

4 May 2024 in Journal of Big Data
Verified
Journal Article
Open access
PDF file
Riccardo CantiniRiccardo Cantini
Riccardo Cantini
AOAlessio Orsino
Alessio Orsino
Domenico TaliaDomenico Talia
Domenico Talia
Large Language Models (LLMs) are characterized by their inherent memory inefficiency and compute-intensive nature, making them impractical to run on low-resource devices and hindering their applicability in edge AI contexts. To address this issue, Knowledge Distillation approaches have been adopted to transfer knowledge from a complex model, referred to as the teacher, to a more compact, computationally efficient one, known as the student. The aim is to retain the performance of the original model while substantially reducing computational requirements. However, traditional knowledge distillation methods may struggle to effectively transfer crucial explainable knowledge from an LLM teacher to the student, potentially leading to explanation inconsistencies and decreased performance. This paper presents DiXtill, a method based on a novel approach to distilling knowledge from LLMs into lightweight neural architectures. The main idea is to leverage local explanations provided by an eXplainable Artificial Intelligence (XAI) method to guide the cross-architecture distillation of a teacher LLM into a self-explainable student, specifically a bi-directional LSTM network.Experimental results show that our XAI-driven distillation method allows the teacher explanations to be effectively transferred to the student, resulting in better agreement compared to classical distillation methods,thus enhancing the student interpretability. Furthermore, it enables the student to achieve comparable performance to the teacher LLM while also delivering a significantly higher compression ratio and speedup compared to other techniques such as post-training quantization and pruning, which paves the way for more efficient and sustainable edge AI applications

15 October 2025 in Machine Learning
Verified
Journal Article
Open access
PDF file
Riccardo CantiniRiccardo Cantini
Riccardo Cantini
AOAlessio Orsino
Alessio Orsino
MRMassimo Ruggiero
Massimo Ruggiero
Domenico TaliaDomenico Talia
Domenico Talia
The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in training data, linguistic imbalances, or adversarial manipulation. Despite mitigation efforts, recent studies show that LLMs remain vulnerable to adversarial attacks that elicit biased outputs. This work proposes a scalable benchmarking framework to assess LLM robustness to adversarial bias elicitation. Our methodology involves: ( i ) systematically probing models across multiple tasks targeting diverse sociocultural biases, ( ii ) quantifying robustness through safety scores using an LLM-as-a-Judge approach, and ( iii ) employing jailbreak techniques to reveal safety vulnerabilities. To facilitate systematic benchmarking, we release a curated dataset of bias-related prompts, named CLEAR-Bias . Our analysis, identifying DeepSeek V3 as the most reliable judge LLM, reveals that bias resilience is uneven, with age, disability, and intersectional biases among the most prominent. Some small models outperform larger ones in safety, suggesting that training and architecture may matter more than scale. However, no model is fully robust to adversarial elicitation, with jailbreak attacks using low-resource languages or refusal suppression proving effective across model families. We also find that successive LLM generations exhibit slight safety gains, while models fine-tuned for the medical domain tend to be less safe than their general-purpose counterparts.

12 March 2026 in IEEE Access
Verified
Journal Article
Open access
Loris BelcastroLoris Belcastro
Loris Belcastro
Fabrizio MarozzoFabrizio Marozzo
Fabrizio Marozzo
AOAlessio Orsino
Alessio Orsino
Domenico TaliaDomenico Talia
Domenico Talia
Paolo TrunfioPaolo Trunfio
Paolo Trunfio
The edge-cloud continuum has emerged as a transformative paradigm that meets the growing demand for low-latency, scalable, end-to-end service delivery by integrating decentralized edge resources with centralized cloud infrastructures. Driven by the exponential growth of IoT-generated data and the need for real-time responsiveness, this continuum features multi-layered architectures. However, its adoption is hindered by infrastructural challenges, fragmented standards, and limited guidance for developers and researchers. Existing surveys rarely tackle practical implementation or recent industrial advances. This survey closes those gaps from a developer-oriented perspective, introducing a conceptual framework for navigating the edge-cloud continuum. We systematically examine architectural models, performance metrics, and paradigms for computation, communication, and deployment, together with enabling technologies and widely used edge-to-cloud platforms.We also discuss real-world applications in smart cities, healthcare, and Industry 4.0, as well as tools for testing and experimentation. Drawing on academic research and practices of leading cloud providers, this survey serves as a practical guide for developers and a structured reference for researchers, while identifying open challenges and emerging trends that will shape the future of the continuum.


5 May 2021 in Future Internet
Verified
Journal Article
Open access
PDF file
Riccardo CantiniRiccardo Cantini
Riccardo Cantini
Fabrizio MarozzoFabrizio Marozzo
Fabrizio Marozzo
AOAlessio Orsino
Alessio Orsino
Domenico TaliaDomenico Talia
Domenico Talia
Paolo TrunfioPaolo Trunfio
Paolo Trunfio
Workflows are largely used to orchestrate complex sets of operations required to handle and process huge amounts of data. Parallel processing is often vital to reduce execution time when complex data-intensive workflows must be run efficiently, and at the same time, in-memory processing can bring important benefits to accelerate execution. However, optimization techniques are necessary to fully exploit in-memory processing, avoiding performance drops due to memory saturation events. This paper proposed a novel solution, called the Intelligent In-memory Workflow Manager (IIWM), for optimizing the in-memory execution of data-intensive workflows on parallel machines. IIWM is based on two complementary strategies: (1) a machine learning strategy for predicting the memory occupancy and execution time of workflow tasks; (2) a scheduling strategy that allocates tasks to a computing node, taking into account the (predicted) memory occupancy and execution time of each task and the memory available on that node. The effectiveness of the machine learning-based predictor and the scheduling strategy were demonstrated experimentally using as a testbed, Spark, a high-performance Big Data processing framework that exploits in-memory computing to speed up the execution of large-scale applications. In particular, two synthetic workflows were prepared for testing the robustness of the IIWM in scenarios characterized by a high level of parallelism and a limited amount of memory reserved for execution. Furthermore, a real data analysis workflow was used as a case study, for better assessing the benefits of the proposed approach. Thanks to high accuracy in predicting resources used at runtime, the IIWM was able to avoid disk writes caused by memory saturation, outperforming a traditional strategy in which only dependencies among tasks are taken into account. Specifically, the IIWM achieved up to a 31% and a 40% reduction of makespan and a performance improvement up to 1.45× and 1.66× on the synthetic workflows and the real case study, respectively.