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.

Visit the official project website: coltrane-v.github.io

• CHAOS: Controlled Hardware fAult injectOr System for gem5
  arXiv

• 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

• 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 | Presentation

Public repositories containing code and tools developed by the COLTRANE-V project:

• Politecnico di Torino (Coordinator), Turin, Italy
• University of Catania, Catania, Italy
• University of Genoa, Genoa, Italy