Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction

Alesia Chernikova
Alesia Chernikova
BaekGyu Kim
BaekGyu Kim

IEEE Symposium on Security and Privacy Workshops, pp. 132-137, 2019.

Cited by: 4|Bibtex|Views39|DOI:https://doi.org/10.1109/SPW.2019.00033
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Deep Neural Networks (DNNs) have tremendous potential in advancing the vision for self-driving cars. However, the security of DNN models in this context leads to major safety implications and needs to be better understood. We consider the case study of steering angle prediction from camera images, using the dataset from the 2014 Udacity...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments