Adversarial Attacks on Multi-task Visual Perception for Autonomous Driving

TL;DR

This paper investigates the vulnerability of multi-task deep neural networks used in autonomous driving to various adversarial attacks, analyzing their impact across multiple perception tasks and evaluating simple defense strategies.

Contribution

It provides a comprehensive analysis of adversarial attacks on multi-task perception networks in autonomous driving, including experiments on different attack types and defenses.

Findings

Adversarial attacks significantly affect perception tasks.

White-box attacks are more effective than black-box attacks.

Simple defenses offer limited protection.

Abstract

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 https://youtu.be/6AixN90budY.