Won Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Won Park has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Benjamin Cyr
Computer Science and Engineering, University of Michigan, Ann Arbor, USA
1 shared publication - Chaowei Xiao
Johns Hopkins University, Baltimore, USA
1 shared publication David Wagner
University of California, Berkeley
1 shared publication- Jason Xinyu Liu
Brown University, Providence, RI, USA
1 shared publication - Kevin Fu
Northeastern University, USA
1 shared publication - Michael McCoyd
University of California, Berkeley
1 shared publication
Latest Publications
- 14 October 2020
- Published by Springer Nature
- p. 564-582
Minority Reports Defense: Defending Against Adversarial Patches
- 14 October 2020
- Published by Springer Nature
- p. 564-582
Minority Reports Defense: Defending Against Adversarial Patches
- Top Cited PapersOpen Access
- 6 November 2019
- Published by Association for Computing Machinery (ACM)
- p. 2267-2281
Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environment. Due to its direct impact on road safety, multiple prior efforts have been made to study its the security of perception systems. In contrast to prior work that concentrates on camera-based perception, in this work we perform the first security study of LiDAR-based perception in AV settings, which is highly important but unexplored. We consider LiDAR spoofing attacks as the threat model and set the attack goal as spoofing obstacles close to the front of a victim AV. We find that blindly applying LiDAR spoofing is insufficient to achieve this goal due to the machine learning-based object detection process. Thus, we then explore the possibility of strategically controlling the spoofed attack to fool the machine learning model. We formulate this task as an optimization problem and design modeling methods for the input perturbation function and the objective function. We also identify the inherent limitations of directly solving the problem using optimization and design an algorithm that combines optimization and global sampling, which improves the attack success rates to around 75%. As a case study to understand the attack impact at the AV driving decision level, we construct and evaluate two attack scenarios that may damage road safety and mobility. We also discuss defense directions at the AV system, sensor, and machine learning model levels. CCS CONCEPTS • Security and privacy → Domain-specific security and
- 6 November 2019
- Published by Association for Computing Machinery (ACM)
- p. 2267-2281
Top Cited PapersOpen AccessAdversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environment. Due to its direct impact on road safety, multiple prior efforts have been made to study its the security of perception systems. In contrast to prior work that concentrates on camera-based perception, in this work we perform the first security study of LiDAR-based perception in AV settings, which is highly important but unexplored. We consider LiDAR spoofing attacks as the threat model and set the attack goal as spoofing obstacles close to the front of a victim AV. We find that blindly applying LiDAR spoofing is insufficient to achieve this goal due to the machine learning-based object detection process. Thus, we then explore the possibility of strategically controlling the spoofed attack to fool the machine learning model. We formulate this task as an optimization problem and design modeling methods for the input perturbation function and the objective function. We also identify the inherent limitations of directly solving the problem using optimization and design an algorithm that combines optimization and global sampling, which improves the attack success rates to around 75%. As a case study to understand the attack impact at the AV driving decision level, we construct and evaluate two attack scenarios that may damage road safety and mobility. We also discuss defense directions at the AV system, sensor, and machine learning model levels. CCS CONCEPTS • Security and privacy → Domain-specific security and