NAISS
SUPR
NAISS Projects
SUPR
Deep Learning-based Misbheavior Detection in IoV
Dnr:

NAISS 2025/22-1223

Type:

NAISS Small Compute

Principal Investigator:

Konstantinos Kalogiannis

Affiliation:

Kungliga Tekniska högskolan

Start Date:

2025-09-12

End Date:

2026-09-01

Primary Classification:

10206: Computer Engineering

Webpage:

Allocation

Abstract

The aim is to evaluate different deep learning models (e.g., transformers, GNNs, BiLSTMs, LSTMs, MLPs, etc) to detect misbehavior in Intelligent Transportation Systems and their applications. We currently have a large dataset of platooning mobility information that includes network and other attacks. We also have an in-city dataset that includes vehicles, pedestrians, etc. Our goal is to investigate the performance of different machine learning architectures in detecting attacks against our datasets and device solutions for safe, reliable, and secure ITS.