Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance System. (arXiv:2306.05358v1 [cs.CR])

There are increasing concerns about malicious attacks on autonomous vehicles.
In particular, inaudible voice command attacks pose a significant threat as
voice commands become available in autonomous driving systems. How to
empirically defend against these inaudible attacks remains an open question.
Previous research investigates utilizing deep learning-based multimodal fusion
for defense, without considering the model uncertainty in trustworthiness. As
deep learning has been applied to increasingly sensitive tasks, uncertainty
measurement is crucial in helping improve model robustness, especially in
mission-critical …

advanced assistance attacks autonomous autonomous driving autonomous vehicles command deep learning driver driving fusion malicious question research sensor system systems threat vehicles voice voice commands