DeepAI AI Chat
Log In Sign Up

Adversarial Attacks on Multi-task Visual Perception for Autonomous Driving

by   Ibrahim Sobh, et al.

Deep neural networks (DNNs) have accomplished impressive success in various applications, including autonomous driving perception tasks, in recent years. On the other hand, current deep neural networks are easily fooled by adversarial attacks. This vulnerability raises significant concerns, particularly in safety-critical applications. As a result, research into attacking and defending DNNs has gained much coverage. In this work, detailed adversarial attacks are applied on a diverse multi-task visual perception deep network across distance estimation, semantic segmentation, motion detection, and object detection. The experiments consider both white and black box attacks for targeted and un-targeted cases, while attacking a task and inspecting the effect on all the others, in addition to inspecting the effect of applying a simple defense method. We conclude this paper by comparing and discussing the experimental results, proposing insights and future work. The visualizations of the attacks are available at


page 1

page 2

page 5

page 6

page 7


SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications

One major factor impeding more widespread adoption of deep neural networ...

Physical Adversarial Attacks on Deep Neural Networks for Traffic Sign Recognition: A Feasibility Study

Deep Neural Networks (DNNs) are increasingly applied in the real world i...

End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering

In the development of advanced driver-assistance systems (ADAS) and auto...

On the Feasibility and Generality of Patch-based Adversarial Attacks on Semantic Segmentation Problems

Deep neural networks were applied with success in a myriad of applicatio...

SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning

Person tracking using computer vision techniques has wide ranging applic...

Online Black-Box Confidence Estimation of Deep Neural Networks

Autonomous driving (AD) and advanced driver assistance systems (ADAS) in...