Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
Abstract
Multi-sensor fusion (MSF) is widely used in autonomous vehicles (AVs) for perception, particularly for 3D object detection with camera and LiDAR sensors. The purpose of fusion is to capitalize on the advantages of each modality while minimizing its weaknesses. Advanced deep neural network (DNN)-based fusion techniques have demonstrated the exceptional and industry-leading performance. Due to the redundant information in multiple modalities, MSF is also recognized as a general defence strategy against adversarial attacks. In this paper, we attack fusion models from the camera modality that is considered to be of lesser importance in fusion but is more affordable for attackers. We argue that the weakest link of fusion models depends on their most vulnerable modality and propose an attack framework that targets advanced camera-LiDAR fusion-based 3D object detection models through camera-only adversarial attacks. Our approach employs a two-stage optimization-based strategy that first thoroughly evaluates vulnerable image areas under adversarial attacks, and then applies dedicated attack strategies for different fusion models to generate deployable patches. The evaluations with six advanced camera-LiDAR fusion models and one camera-only model indicate that our attacks successfully compromise all of them. Our approach can either decrease the mean average precision (mAP) of detection performance from 0.824 to 0.353 or degrade the detection score of a target object from 0.728 to 0.156, demonstrating the efficacy of our proposed attack framework. Code is available.
Cite
Text
Cheng et al. "Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection." International Conference on Learning Representations, 2024.Markdown
[Cheng et al. "Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection." International Conference on Learning Representations, 2024.](https://mlanthology.org/iclr/2024/cheng2024iclr-fusion/)BibTeX
@inproceedings{cheng2024iclr-fusion,
title = {{Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection}},
author = {Cheng, Zhiyuan and Choi, Hongjun and Feng, Shiwei and Liang, James Chenhao and Tao, Guanhong and Liu, Dongfang and Zuzak, Michael and Zhang, Xiangyu},
booktitle = {International Conference on Learning Representations},
year = {2024},
url = {https://mlanthology.org/iclr/2024/cheng2024iclr-fusion/}
}