Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system

Autonomous Vehicles are becoming increasingly important and relevant in today’s world. Their applications can be found everywhere, from public transport to overcome land and workforce constraints to personal uses for convenience to business uses for freight transportation and utility services sec...

Full description

Saved in:
Bibliographic Details
Main Author: Chia, Yi You
Other Authors: Tan Rui
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/156782
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-156782
record_format dspace
spelling sg-ntu-dr.10356-1567822022-04-23T13:04:47Z Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system Chia, Yi You Tan Rui School of Computer Science and Engineering tanrui@ntu.edu.sg Engineering::Computer science and engineering Autonomous Vehicles are becoming increasingly important and relevant in today’s world. Their applications can be found everywhere, from public transport to overcome land and workforce constraints to personal uses for convenience to business uses for freight transportation and utility services sectors. Therefore, emphasising the importance of safety in these autonomous vehicles. Autonomous vehicles use Autonomous Driving Systems (ADS), which requires inputs from multiple camera sensors to be passed into a machine learning model to output the results that directly control the car movements. This paper focuses on the safety of these machine learning models. A black-box Universal Adversarial Network (UAN) is first trained to create a universal perturbation, which will be used to attack the machine learning model that recognises traffic light signals. Eventually producing a wrong traffic signal as an output. Multiple variations of the UAN are produced to study their effect on the accuracy of these machine learning models. This vulnerability will also be studied in a realistic environment using Baidu Apollo ADS and LGSVL. Lastly, basic defences of Apollo ADS will be explored. Bachelor of Engineering (Computer Science) 2022-04-23T13:04:47Z 2022-04-23T13:04:47Z 2022 Final Year Project (FYP) Chia, Y. Y. (2022). Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156782 https://hdl.handle.net/10356/156782 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
spellingShingle Engineering::Computer science and engineering
Chia, Yi You
Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system
description Autonomous Vehicles are becoming increasingly important and relevant in today’s world. Their applications can be found everywhere, from public transport to overcome land and workforce constraints to personal uses for convenience to business uses for freight transportation and utility services sectors. Therefore, emphasising the importance of safety in these autonomous vehicles. Autonomous vehicles use Autonomous Driving Systems (ADS), which requires inputs from multiple camera sensors to be passed into a machine learning model to output the results that directly control the car movements. This paper focuses on the safety of these machine learning models. A black-box Universal Adversarial Network (UAN) is first trained to create a universal perturbation, which will be used to attack the machine learning model that recognises traffic light signals. Eventually producing a wrong traffic signal as an output. Multiple variations of the UAN are produced to study their effect on the accuracy of these machine learning models. This vulnerability will also be studied in a realistic environment using Baidu Apollo ADS and LGSVL. Lastly, basic defences of Apollo ADS will be explored.
author2 Tan Rui
author_facet Tan Rui
Chia, Yi You
format Final Year Project
author Chia, Yi You
author_sort Chia, Yi You
title Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system
title_short Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system
title_full Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system
title_fullStr Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system
title_full_unstemmed Universal adversarial network attacks on traffic light recognition of Apollo autonomous driving system
title_sort universal adversarial network attacks on traffic light recognition of apollo autonomous driving system
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/156782
_version_ 1731235810325299200