Physically Realizable Adversarial Examples for LiDAR Object Detection
By James Tu, Mengye Ren, Sivabalan Manivasagam, Ming Liang, Binh Yang, R. Du, Frank Cheng, Raquel Urtasun. Computer Vision and Pattern Recognition, 2020
308 citations recorded by the source corpus.
Modern autonomous driving systems rely heavily on deep learning models to process point cloud sensory data; meanwhile, deep models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Despite the fact that this poses a security concern for the self-driving industry, there has been very little exploration in terms of 3D perception, as most adversarial attacks have only been applied to 2D flat images. In this paper, we address this issue and present a method to generate universal 3D adversarial objects to fool LiDAR detectors. In particular, we demonstrate that placing an adversarial object on the rooftop of any target vehicle to hide the vehicle entirely from LiDAR detectors with a success rate of 80%. We report attack results on a suite of detectors using various input representation of point clouds. We also conduct a pilot study on adversarial defense using data augmentation. This is one step closer towards safer self-driving under unseen conditions from limited training data.
Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Molecular Biology
View Paper: https://www.semanticscholar.org/paper/d4f462f00720101cfb66259525ade4255b506a41
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ajmal Saeed Mian
- Mubarak Shah
- Navid Kardan
- Naveed Akhtar
- Hossein Rahmani
- Luc Van Gool
- Chen Sun
- Andrew Zisserman
In Electrical and Electronic Engineering
In Molecular Biology
Citations in the corpus
- Decoupling Deep Learning for Interpretable Image Recognition (2022, unknown): “The previous mask-based methods [6, 4, 32] only perform activation consistent learning for masking the same size as the original image, which is prone to adversarial effects [29].”
- Advances in adversarial attacks and defenses in computer vision: A survey (2021, methodology): “semantic segmentation [23], [24]; object detection [25], [26]; and object tracking [27], [28].”