|
JAIST Repository >
School of Information Science >
Articles >
Journal Articles >
Please use this identifier to cite or link to this item:
https://hdl.handle.net/10119/19964
|
| Title: | Shortcut-enhanced Multimodal Backdoor Attack in Vision-guided Robot Grasping |
| Authors: | Li, Chenghao
Gao, Ziyan
Chong, Nak Young |
| Keywords: | Backdoor attack
robot grasping
shortcut learning
multimodality
AI security
human-robot interaction |
| Issue Date: | 2025-07-16 |
| Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
| Magazine name: | IEEE Transactions on Automation Science and Engineering |
| Start page: | 1 |
| End page: | 1 |
| DOI: | 10.1109/TASE.2025.3589764 |
| Abstract: | Integrating the Artificial Intelligence (AI) vision module into the robot grasping system can significantly improve its generalizability, thereby enhancing the efficiency of Human-Robot Interaction (HRI). However, the inherent lack of interpretability in AI also opens the gate to external threats. In this work, we reveal a novel safety risk in this vision-guided robot grasping system by proposing the Shortcut-enhanced Multimodal Backdoor Attack (SEMBA), which can manipulate the grasp quality score using the backdoor trigger leading to a misguided grasping sequence. The SEMBA may thus cause potentially hazardous grasping and pose a threat to human safety in HRI. Specifically, we initially present the Multimodal Shortcut Searching Algorithm (MSSA) to find the pixel value that deviates the most from the mean and standard deviation of the multimodal dataset, along with the pivotal pixel position for individual images. This will guarantee that the proposed attack is effective in complex, multi-class object scenarios. Next, based on MSSA, we devise the Multimodal Trigger Generator (MTG) to create diverse multimodal backdoor triggers and integrate them into the dataset, ensuring that our attack has the multimodality attribute. We conduct extensive experiments on the benchmark datasets and a cobot, showing the effectiveness of the proposed method both in the digital and physical worlds. Our demo videos are available in supplementary items. |
| Rights: | Copyright (c) 2025 Authors. Chenghao Li, Ziyan Gao, and Nak Young Chong. IEEE Transactions on Automation Science and Engineering (Early Access), 2025. This is an Open Access article distributed under the terms of Creative Commons Licence CC-BY [https://creativecommons.org/licenses/by/4.0/]. Original publication is available on IEEE Xplore via https://doi.org/10.1109/TASE.2025.3589764. |
| URI: | https://hdl.handle.net/10119/19964 |
| Material Type: | author |
| Appears in Collections: | b10-1. 雑誌掲載論文 (Journal Articles)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| N-CHONG-I-0722-2.pdf | | 40236Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
