Adversarial example construction against autonomous vehicles
With autonomous vehicles (AVs) approaching widespread adoption, there is a need to emphasize safety as it must not be neglected. Touted to be free from errors commonly made by humans, they are nevertheless not immune to attacks with malicious intent. In general, AVs utilize a variety of machine-l...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/171944 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-171944 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1719442023-11-17T15:37:22Z Adversarial example construction against autonomous vehicles Loh, Zhi Heng Tan Rui School of Computer Science and Engineering tanrui@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence With autonomous vehicles (AVs) approaching widespread adoption, there is a need to emphasize safety as it must not be neglected. Touted to be free from errors commonly made by humans, they are nevertheless not immune to attacks with malicious intent. In general, AVs utilize a variety of machine-learning models and sensors to help them understand their environment. However, based on past research on machine learning models, it is understood that they may be susceptible to adversarial attacks. In this paper, Daedalus, an attack algorithm that exploits the vulnerability in Non-Maximum Suppression (NMS) is used to generate adversarial examples using a surrogate model. The perturbations on the images are nearly imperceptible. The generated images are subsequently evaluated against the Single-Stage Monocular 3D Object Detection via Key Point Estimation [1] (SMOKE) utilized in Baidu Apollo’s Autonomous Driving System for camera-based object detection. In addition, look into potential mitigations that could be implemented to mitigate Daedalus. Bachelor of Engineering (Computer Engineering) 2023-11-17T03:24:47Z 2023-11-17T03:24:47Z 2023 Final Year Project (FYP) Loh, Z. H. (2023). Adversarial example construction against autonomous vehicles. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/171944 https://hdl.handle.net/10356/171944 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::Computing methodologies::Artificial intelligence |
spellingShingle |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Loh, Zhi Heng Adversarial example construction against autonomous vehicles |
description |
With autonomous vehicles (AVs) approaching widespread adoption, there is a need to
emphasize safety as it must not be neglected. Touted to be free from errors commonly
made by humans, they are nevertheless not immune to attacks with malicious intent.
In general, AVs utilize a variety of machine-learning models and sensors to help them
understand their environment. However, based on past research on machine learning
models, it is understood that they may be susceptible to adversarial attacks. In this
paper, Daedalus, an attack algorithm that exploits the vulnerability in Non-Maximum
Suppression (NMS) is used to generate adversarial examples using a surrogate model.
The perturbations on the images are nearly imperceptible. The generated images are
subsequently evaluated against the Single-Stage Monocular 3D Object Detection via
Key Point Estimation [1] (SMOKE) utilized in Baidu Apollo’s Autonomous Driving
System for camera-based object detection. In addition, look into potential mitigations
that could be implemented to mitigate Daedalus. |
author2 |
Tan Rui |
author_facet |
Tan Rui Loh, Zhi Heng |
format |
Final Year Project |
author |
Loh, Zhi Heng |
author_sort |
Loh, Zhi Heng |
title |
Adversarial example construction against autonomous vehicles |
title_short |
Adversarial example construction against autonomous vehicles |
title_full |
Adversarial example construction against autonomous vehicles |
title_fullStr |
Adversarial example construction against autonomous vehicles |
title_full_unstemmed |
Adversarial example construction against autonomous vehicles |
title_sort |
adversarial example construction against autonomous vehicles |
publisher |
Nanyang Technological University |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/171944 |
_version_ |
1783955542297804800 |