Universal adversarial example construction against autonomous vehicle
Autonomous Vehicles (AVs) have seen a rapid pace of development and made significant strides in technological capabilities. While AVs do not suffer from human error, they are not immune to other types of errors and even more worryingly, malicious attacks. Most AVs today utilize multiple machine lear...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/153501 |
| _version_ | 1811680071847510016 |
|---|---|
| author | Beh, Nicholas Chee Kwang |
| author2 | Tan Rui |
| author_facet | Tan Rui Beh, Nicholas Chee Kwang |
| author_sort | Beh, Nicholas Chee Kwang |
| collection | NTU |
| description | Autonomous Vehicles (AVs) have seen a rapid pace of development and made significant strides in technological capabilities. While AVs do not suffer from human error, they are not immune to other types of errors and even more worryingly, malicious attacks. Most AVs today utilize multiple machine learning models which may or may not be resistant against adversarial attacks. A white-box attack conducted using Universal Adversarial Perturbations (Iterative-DeepFool) on the traffic light recognition component of the Baidu Apollo Autonomous Driving System (ADS) platform revealed that the model failed to hold up in conditions other than daylight. Furthermore, the perturbation is imperceptible to the human eye, posing an even greater safety risk. We also explore the current safeguards in place in Apollo and hypothesize potential solutions to mitigate this issue. |
| first_indexed | 2024-10-01T03:19:14Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/153501 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:19:14Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1535012021-12-06T03:10:13Z Universal adversarial example construction against autonomous vehicle Beh, Nicholas Chee Kwang Tan Rui School of Computer Science and Engineering tanrui@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Autonomous Vehicles (AVs) have seen a rapid pace of development and made significant strides in technological capabilities. While AVs do not suffer from human error, they are not immune to other types of errors and even more worryingly, malicious attacks. Most AVs today utilize multiple machine learning models which may or may not be resistant against adversarial attacks. A white-box attack conducted using Universal Adversarial Perturbations (Iterative-DeepFool) on the traffic light recognition component of the Baidu Apollo Autonomous Driving System (ADS) platform revealed that the model failed to hold up in conditions other than daylight. Furthermore, the perturbation is imperceptible to the human eye, posing an even greater safety risk. We also explore the current safeguards in place in Apollo and hypothesize potential solutions to mitigate this issue. Bachelor of Engineering (Computer Science) 2021-12-06T03:10:13Z 2021-12-06T03:10:13Z 2021 Final Year Project (FYP) Beh, N. C. K. (2021). Universal adversarial example construction against autonomous vehicle. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153501 https://hdl.handle.net/10356/153501 en SCSE20-0841 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Beh, Nicholas Chee Kwang Universal adversarial example construction against autonomous vehicle |
| title | Universal adversarial example construction against autonomous vehicle |
| title_full | Universal adversarial example construction against autonomous vehicle |
| title_fullStr | Universal adversarial example construction against autonomous vehicle |
| title_full_unstemmed | Universal adversarial example construction against autonomous vehicle |
| title_short | Universal adversarial example construction against autonomous vehicle |
| title_sort | universal adversarial example construction against autonomous vehicle |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/153501 |
| work_keys_str_mv | AT behnicholascheekwang universaladversarialexampleconstructionagainstautonomousvehicle |