Alessandro Balestrucci
RttBiografia
Alessandro Balestrucci è un ricercatore in tenure track presso l'Università Mercatorum, dove co-insegna il corso di Sicurezza e Protezione dei Sistemi Informatici. Ha precedentemente lavorato all'Università di Milano e al CINI come postdoc, concentrandosi sulla robustezza dei modelli di machine learning e sulle strategie di mitigazione di dataset poisoning. Durante il suo periodo al CINI, ha contribuito a progetti come PALM e IMPETUS, migliorando la resilienza dei modelli di machine learning contro attacchi avversari e lavorando sulle politiche di controllo degli accessi e strategie di governance dei dati sicure. I suoi interessi di ricerca includono: intelligenza artificiale (AI) & machine learning (ML) e mitigazione di disinformazione mirata su social media. Ha conseguito il PhD in Computer Science al Gran Sasso Science Institute; la laurea magistrale con lode in Informatica all'Università di Bari; e l'abilitazione alla professione di Ingegnere ICT.
Facoltà
Materia d'insegnamento
- Sicurezza e protezione dei dati e dei sistemi informatici (CdL Sicurezza Informatica - LM-66)
Dipartimento
Docente di riferimento
LM-66 - Sicurezza Informatica
Modalità di prenotazione degli uffici
Pubblicazioni
On the robustness of random forest against untargeted data poisoning: An ensemble-based approachM Anisetti, CA Ardagna, A Balestrucci, ... (2023)IEEE Transactions …, ieeexplore.ieee.org, cited by 14 (7.00 per year)
<https://ieeexplore.ieee.org/abstract/document/10175648/>
Machine learning is becoming ubiquitous. From finance to medicine, machine learning models are boosting decision-making processes and even outperforming humans in some …
-----
Dynamic and scalable enforcement of access control policies for big dataM Anisetti, CA Ardagna, C Braghin, E Damiani, A Balestrucci... (2021)Proceedings of the 13th …, dl.acm.org, cited by 23 (5.75 per year)
<https://doi.org/10.1145/3444757.3485107>
The conflict between the need of protecting and sharing data is hampering the spread of big data applications. Security and privacy assurance is required to protect data owners, while …
-----
Writing generation model for health care neuromuscular system investigationD Impedovo, G Pirlo, FM Mangini, D Barbuzzi, A Balestrucci... (2014)… Intelligence Methods for …, Springer, cited by 34 (3.09 per year)
<https://doi.org/10.1007/978-3-319-09042-9_10>
In this paper the use of handwriting for health investigation is addressed. For the purpose, the paper first presents the Delta-Log and Sigma-Log models to investigate on the …
-----
A behavioural analysis of credulous Twitter usersA Balestrucci, R De Nicola, M Petrocchi, ... (2021)Online Social Networks …, Elsevier, cited by 16 (4.00 per year)
<https://www.sciencedirect.com/science/article/pii/S2468696421000173>
Thanks to platforms such as Twitter and Facebook, people can know facts and events that otherwise would have been silenced. However, social media significantly contribute also to …
-----
Credulous users and fake news: A real case study on the propagation in TwitterA Balestrucci, R De Nicola (2020)2020 IEEE Conference on …, ieeexplore.ieee.org, cited by 16 (3.20 per year)
<https://ieeexplore.ieee.org/abstract/document/9122764/>
Recent studies have confirmed a growing trend, especially among youngsters, of using Online Social Media as favourite information platform at the expense of traditional mass …
-----
Identification of credulous users on TwitterA Balestrucci, R De Nicola, O Inverso, ... (2019)Proceedings of the 34th …, dl.acm.org, cited by 18 (3.00 per year)
<https://doi.org/10.1145/3297280.3297486>
Social networks can quickly propagate information to large audiences and can be used to spread fake news or to provide false figures of popularity. Social bots, ie, software robots that …
-----
Do you really follow them? automatic detection of credulous Twitter usersA Balestrucci, R De Nicola, M Petrocchi, ... (2019)… Data Engineering and …, Springer, cited by 14 (2.33 per year)
<https://doi.org/10.1007/978-3-030-33607-3_44>
Abstract Online Social Media represent a pervasive source of information able to reach a huge audience. Sadly, recent studies show how online social bots (automated, often …
-----
How many bots are you following?A Balestrucci (2020)ITASEC 2020
Social Media are evolving as a pervasive source of news able to reach a larger audience through their spreading power. The main drawback is given by the presence of malicious …
-----
Handwritten processing for pre diagnosis of Alzheimer diseaseD Impedovo, G Pirlo, D Barbuzzi, A Balestrucci, ... (2014)BIODEVICES …, ricerca.uniba.it, cited by 7 (0.64 per year)
<https://ricerca.uniba.it/handle/11586/138468>
Based on neuromuscular transfer function of the handwriting system, in this paper a non invasive pre diagnosis system for Alzheimer disease alert is proposed. It is well known in …
-----
Potential target audience of misinformation on Social Media: Credulous UsersA Balestrucci (2020)tesidottorato.depositolegale.it, cited by 1 (0.20 per year)
<https://tesidottorato.depositolegale.it/handle/20.500.14242/116478>
The capability to reach a wider audience and the possibility to disseminate news faster are the main reasons for the growing importance of Online Social Media (OSM) whose usage …
Le Principali aree di ricerca in ambito accademico riguardano:
- Machine Learning e Intelligenza artificiale
- Bioinformatica
- Sicurezza dei sistemi informatici
- Mitigazione di disinformazione mirata
- Robustezza di modelli di ML contro data poisoning