COLTRANE-V

COntinous Learning capabilities for funcTional safety Run-time threAts maNagEment in Automotive RISC-V based ECU

COLTRANE-V is a PRIN 2022 project (2022HWM3T9, 2023-2025) coordinated by Politecnico di Torino and funded by the Italian Ministry of University and Research. The project aims to improve the dependability of automotive ECUs through a continuous learning approach: detection of faults and attacks together with real-time countermeasures on a RISC-V architecture with an AI accelerator, in collaboration with the University of Catania and the University of Genoa.

Team

Politecnico di Torino — SMILIES group

Portrait of Alessandro Savino

Prof. Alessandro Savino

Associate Professor at the Department of Control and Computer Engineering (DAUIN) of Politecnico di Torino and deputy director of the SMILIES group. His research focuses on hardware/software dependability and security for safety-critical systems, approximate computing, and sustainable computing.

ORCIDORCID 📧 Contact
Portrait of Luca Mannella

Dr. Luca Mannella

Postdoctoral researcher at the Department of Control and Computer Engineering (DAUIN) of Politecnico di Torino. His work focuses on cybersecurity, IoT, and software engineering, with particular attention to the security of connected home platforms and automotive systems.

ORCIDORCID 📧 Contact
Portrait of Tamer Ahmed Eltaras

Tamer Ahmed Eltaras

Researcher at the Department of Control and Computer Engineering (DAUIN) of Politecnico di Torino. His work focuses on cybersecurity and privacy in AI, with particular attention to gradient inversion attacks (R-CONV / R-CONV++) and AI-based classification of adversarial attacks and hardware corruptions in the split computing context. He has also contributed to studies on federated learning and privacy-preserving aggregation.

ORCIDORCID 📧 Contact

University of Catania

Portrait of Maurizio Palesi

Prof. Maurizio Palesi

Full Professor at the Department of Electrical, Electronic and Computer Engineering (DIEEI) of the University of Catania. His research focuses on the design and optimization of advanced computing architectures, especially multi-core systems and Network-on-Chip solutions, with attention to performance and energy efficiency.

ORCIDORCID 📧 Contact
Portrait of Elio Vinciguerra

Elio Vinciguerra

Researcher at the Department of Electrical, Electronic and Computer Engineering (DIEEI) of the University of Catania. His work focuses on architectures and tools for evaluating dependability and security, including fault injection techniques (for example on gem5) and methods for emerging architectures.

ORCIDORCID 📧 Contact

University of Genoa

Portrait of Alessandro Armando

Prof. Alessandro Armando

Full Professor at the Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS) of the University of Genoa. His research focuses on cybersecurity, especially the formal verification of security protocols, vulnerability analysis, and trust management.

ORCIDORCID 📧 Contact
Portrait of Luca Verderame

Prof. Luca Verderame

Associate Professor at the Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS) of the University of Genoa. His work focuses on cybersecurity with an emphasis on mobile security (Android): static and dynamic analysis, testing, and application protection techniques.

ORCIDORCID 📧 Contact
Portrait of Alessio Merlo

Prof. Alessio Merlo

Full Professor of Information Processing Systems at the Centro Alti Studi per la Difesa (CASD) in Rome, and adjunct professor at the Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS) of the University of Genoa. His research focuses on cybersecurity with a strong emphasis on mobile security (Android): static and dynamic analysis, testing, and protection techniques.

ORCIDORCID 📧 Contact

Publications

Below is a selection of articles and papers published by the COLTRANE-V team.

2026

  • CHAOS: Controlled Hardware fAult injectOr System for gem5 — arXiv

2025

  • Real-time Embedded System Fault Injector Framework for Micro-architectural State Based Reliability Assessment — Journal of Electronic Testing (Springer) — DOI | IRIS
  • CANDoSA: A Hardware Performance Counter-Based Intrusion Detection System for DoS Attacks on Automotive CAN bus — IEEE IOLTS 2025 — DOI | arXiv | Poster
  • AI-based Classification of Intentional vs. Unintentional Corruptions in the Split Computing context — IEEE IOLTS 2025 — DOI | IRIS | Presentation
  • Uncovering Privacy Vulnerabilities through Analytical Gradient Inversion Attacks — Springer — DOI | arXiv
  • An Anomaly Detection Model for RISC-V in Automotive Applications: A Domain-Specific Accelerator Perspective — IEEE PDP 2025 — DOI | IEEE Xplore

2024

  • R-CONV: An Analytical Approach for Efficient Data Reconstruction via Convolutional Gradients — Springer LNCS, WISE 2024 — DOI | arXiv | Presentation
  • CARACAS: vehiCular ArchitectuRe for detAiled Can Attacks Simulation — IEEE ISCC 2024 — DOI | arXiv | Presentation
  • A Micro Architectural Events Aware Real-Time Embedded System Fault Injector — IEEE LATS 2024 — DOI | arXiv | Presentation

Project Repositories

Public repositories containing code and tools developed during the project.
Visit our GitHub organization as well github.com/COLTRANE-V .

Repository Name Description Link Paper
CHAOS Controlled Hardware fAult injectOr System for gem5 GitHub CHAOS (2026)
SAFER-V Real-time Embedded System Fault Injector Framework for RISC-V GitHub Real-time Fault Injector (2025)
CARACAS vehiCular ArchitectuRe for detAiled Can Attacks Simulation GitHub CARACAS (2024)
R-CONV An Analytical Approach for Efficient Data Reconstruction via Convolutional Gradients GitHub R-CONV (2024)