Cybersecurity for AI-Augmented Systems

Informazioni relative al progetto

Sec4AI4Sec

ID dell’accordo di sovvenzione: 101120393

DOI

10.3030/101120393

Data della firma CE 11 Luglio 2023

Data di avvio 1 Ottobre 2023

Data di completamento 30 Settembre 2026

Finanziato da

• Civil Security for Society

Costo totale

€ 4 283 037,50

Contributo UE

€ 4 283 037,50

Coordinato da

UNIVERSITA DEGLI STUDI DI TRENTO
Italy

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (7)

Interim Open Science Results

Description of the components available as Open Science (dataset) (T2.2).

Communication and Dissemination Strategy

List of Sec4AI4Sec dissemination targets, channels and activities the project will use to reach them, and the related plan for each identified pathway (T2.1, T 2.2 and T2.3).

Sec4AI4Sec Integrated Toolflow Evaluation and Demonstration Plan – Report

Framework for the execution of the demonstrations to be run in T7.2 to T7.4, defining KPIs for the evaluation of the toolflow.

Interim Report on Communication and Dissemination

A report on general and pathway's dissemination and communication activities and results (T2.1, T2.2 and T2.3).

Initial Report on Evaluation of Trustworthy AI Models

Taxonomy of attacks against AI models (T4.1, T4.2) O3.R6, O3.R7

Intermediate Report on the Assurance Methodologies for Products and Services

Design and rules for security and gaps for AI/ML components (T6.1) O1.R1

ML-based Methods for Vulnerability Assessment - v1

Description of the projects approaches and tools for vulnerability assessment (T3.3) O5.R11

Data sets, microdata, etc (1)

Repository Mining Toolkit -v1

Design and first implementation of the repository mining toolkit (T3.1) O2.R3, P3.1

Websites, patent fillings, videos etc. (1)

Internet and Social Media Presences

The first release of the projects website (activities on T2.3).

Pubblicazioni

Peer reviewed articles (7)

Known Vulnerabilities of Open Source Projects: Where Are the Fixes?

Autori: Antonino Sabetta; Serena Elisa Ponta; Rocio Cabrera Lozoya; Michele Bezzi; Tommaso Sacchetti; Matteo Greco; Gergő Balogh; Péter Hegedűs; Rudolf Ferenc; Ranindya Paramitha; Ivan Pashchenko; Aurora Papotti; Ákos Milánkovich; Fabio Massacci
Pubblicato in: IEEE Security & Privacy, 2024, ISSN 1558-4046
Editore: IEEE
DOI: 10.1109/msec.2023.3343836

On the acceptance by code reviewers of candidate security patches suggested by Automated Program Repair tools

Autori: Aurora Papotti, Ranindya Paramitha, Fabio Massacci
Pubblicato in: Empirical Software Engineering, Numero 29, 2024, ISSN 1382-3256
Editore: Springer Science and Business Media LLC
DOI: 10.1007/s10664-024-10506-z

A Case-Control Study to Measure Behavioral Risks of Malware Encounters in Organizations

Autori: Marcello Meschini, Giorgio Di Tizio, Marco Balduzzi, Fabio Massacci
Pubblicato in: IEEE Transactions on Information Forensics and Security, Numero 19, 2024, ISSN 1556-6013
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIFS.2024.3456960

Addressing combinatorial experiments and scarcity of subjects by provably orthogonal and crossover experimental designs

Autori: Fabio Massacci, Aurora Papotti, Ranindya Paramitha
Pubblicato in: Journal of Systems and Software, Numero 211, 2024, ISSN 0164-1212
Editore: Elsevier BV
DOI: 10.1016/j.jss.2024.111990

Technical leverage analysis in the Python ecosystem

Autori: Ranindya Paramitha, Fabio Massacci
Pubblicato in: Empirical Software Engineering, Numero 28, 2024, ISSN 1382-3256
Editore: Springer Science and Business Media LLC
DOI: 10.1007/s10664-023-10355-2

HO-FMN: Hyperparameter optimization for fast minimum-norm attacks

Autori: Raffaele Mura, Giuseppe Floris, Luca Scionis, Giorgio Piras, Maura Pintor, Ambra Demontis, Giorgio Giacinto, Battista Biggio, Fabio Roli
Pubblicato in: Neurocomputing, Numero 616, 2024, ISSN 0925-2312
Editore: Elsevier BV
DOI: 10.1016/j.neucom.2024.128918

APR4Vul: an empirical study of automatic program repair techniques on real-world Java vulnerabilities

Autori: Quang-Cuong Bui, Ranindya Paramitha, Duc-Ly Vu, Fabio Massacci, Riccardo Scandariato
Pubblicato in: Empirical Software Engineering, Numero 29, 2024, ISSN 1382-3256
Editore: Springer Science and Business Media LLC
DOI: 10.1007/s10664-023-10415-7

Book chapters (2)

Towards the Use of Domain Knowledge to Enhance Transformer-Based Vulnerability Detection

Autori: Alessandro Marchetto, Rosmaël Zidane Lekeufack Foulefack
Pubblicato in: Communications in Computer and Information Science, Quality of Information and Communications Technology, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-70245-7_26

A Rapid Review on Graph-Based Learning Vulnerability Detection

Autori: Rosmaël Zidane Lekeufack Foulefack, Alessandro Marchetto
Pubblicato in: Communications in Computer and Information Science, Quality of Information and Communications Technology, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-70245-7_25

Conference proceedings (4)

Can explainability and deep-learning be used for localizing vulnerabilities in source code?

Autori: Alessandro Marchetto
Pubblicato in: Proceedings of the 5th ACM/IEEE International Conference on Automation of Software Test (AST 2024), 2024
Editore: ACM
DOI: 10.1145/3644032.3644448

Hash4Patch: A Lightweight Low False Positive Tool for Finding Vulnerability Patch Commits

Autori: Simone Scalco, Ranindya Paramitha
Pubblicato in: Proceedings of the 21st International Conference on Mining Software Repositories, 2024
Editore: ACM
DOI: 10.1145/3643991.3644871

Designing Secure AI-based Systems: a Multi-Vocal Literature Review

Autori: Simon Schneider, Ananya Saha, Emanuele Mezzi, Katja Tuma, Riccardo Scandariato
Pubblicato in: 2024 IEEE Secure Development Conference (SecDev), 2024
Editore: IEEE
DOI: 10.1109/SecDev61143.2024.00007

Adversarial Testing with Reinforcement Learning: A Case Study on Autonomous Driving

Autori: Andréa Doreste, Matteo Biagiola, Paolo Tonella
Pubblicato in: 2024 IEEE Conference on Software Testing, Verification and Validation (ICST), 2024
Editore: IEEE
DOI: 10.1109/ICST60714.2024.00034