DeepAI AI Chat
Log In Sign Up

Adversarial Driving: Attacking End-to-End Autonomous Driving Systems

by   Han Wu, et al.

As the research in deep neural networks advances, deep convolutional networks become feasible for automated driving tasks. There is an emerging trend of employing end-to-end models in the automation of driving tasks. However, previous research unveils that deep neural networks are vulnerable to adversarial attacks in classification tasks. While for regression tasks such as autonomous driving, the effect of these attacks remains uncertain. In this research, we devise two white-box targeted attacks against end-to-end autonomous driving systems. The driving model takes an image as input and outputs the steering angle. Our attacks can manipulate the behaviour of the autonomous driving system only by changing the input image. The implementation of both attacks can achieve real-time performance on CPUs. This demo aims to raise concerns over applications of end-to-end models in safety-critical systems.


Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models

Recent advances in machine learning, especially techniques such as deep ...

Fast Recurrent Fully Convolutional Networks for Direct Perception in Autonomous Driving

Deep convolutional neural networks (CNNs) have been shown to perform ext...

Understanding Time Variations of DNN Inference in Autonomous Driving

Deep neural networks (DNNs) are widely used in autonomous driving due to...

A General Framework for Uncertainty Estimation in Deep Learning

End-to-end learning has recently emerged as a promising technique to tac...

Towards Greener Solutions for Steering Angle Prediction

In this paper, we investigate the two most popular families of deep neur...

Marginally calibrated response distributions for end-to-end learning in autonomous driving

End-to-end learners for autonomous driving are deep neural networks that...

Attacking Vision-based Perception in End-to-End Autonomous Driving Models

Recent advances in machine learning, especially techniques such as deep ...

Code Repositories


Adversarial Driving v.s. Autonomous Driving.

view repo