SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.01907 · 2019

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advances in machine learning, especially techniques such as deep neural networks, are enabling a range of emerging applications. One such example is autonomous driving, which often relies on deep learning for perception. However, deep learning-based perception has been shown to be vulnerable to a host of subtle adversarial manipulations of images. Nevertheless, the vast majority of such demonstrations focus on perception that is disembodied from end-to-end control. We present novel end-to-end attacks on autonomous driving in simulation, using simple physically realizable attacks: the painting of black lines on the road. These attacks target deep neural network models for end-to-end autonomous driving control. A systematic investigation shows that such attacks are easy to engineer, and we describe scenarios (e.g., right turns) in which they are highly effective. We define several objective functions that quantify the success of an attack and develop techniques based on Bayesian Optimization to efficiently traverse the search space of higher dimensional attacks. Additionally, we define a novel class of hijacking attacks, where painted lines on the road cause the driver-less car to follow a target path. Through the use of network deconvolution, we provide insights into the successful attacks, which appear to work by mimicking activations of entirely different scenarios. Our code is available at https://github.com/xz-group/AdverseDrive

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1910.01907")
get_code_for_paper("1910.01907")
have("1910.01907")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1910.01907.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1910.01907.svg)](https://syntology.ai/paper/1910.01907)

Connect an agent — have() is free.