16775 research outputs found
Sort by
Shortcut-enhanced Multimodal Backdoor Attack in Vision-guided Robot Grasping
No full textIntegrating 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
mRTA法：誤情報を活用するRetrospective Think-Aloud法
Get PDF定性調査やユーザビリティテストで用いられているRetrospective Think-Aloud法には，十分な発話量が得られなかったり記憶の正確な想起が難しかったりするなどの問題がある．本研究ではこれらの問題を解決するために，Retrospective Think-Aloud法の実施時に提示するタスク遂行時の記録情報に誤情報を混入する方法であるmRTA法を提案する．実験の結果，戦略分析を目的としたmRTA法は，熟達度の高い発話者に対しては記憶の正確な想起と発話量の増加に有効であることを確認した．The Retrospective Think-Aloud method used in qualitative research and usability testing has problems such as not being able to obtain sufficient speech volume or accurately recalling memories. In this study, we propose the mRTA method, which is a method of mixing misinformation into the recorded information of task execution presented during the Retrospective Think-Aloud method to solve these problems. As a result of the experiment, we confirmed that the mRTA method is effective for highly skilled workers in terms of accurate recall of memory and an increase in the amount of speech