.png){kind=icon}
返回
Physics-constrained attack against convolution-based human motion prediction
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2024.127272.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Human motion prediction has achieved a brilliant performance with the help of convolution -based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks. The adversarial attack will encounter problems against human motion prediction in naturalness and data scale. To solve the problems above, we propose a new adversarial attack method that generates the worst -case perturbation by maximizing the human motion predictor's prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution -based human motion prediction models are vulnerable to the proposed attack. Based on the experimental results, we provide insights on how to enhance the adversarial robustness of the human motion predictor and how to improve the adversarial attack against human motion prediction. The code is available at https://github.com/ChengxuDuan/advHMP.
Keyword:
DNN security
Adversarial robustness
Adversarial attack
Human motion prediction
Convolution-based network
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
分享收藏
Switched projected gradient descent algorithms for secure state estimation under sparse sensor attacks.png)
AUTOMATICA
AUTOMATICAIF5.9
PREAI
分享收藏分享收藏Corridor use by small mammals: field measurement for three experimental types of Peromyscus leucopus
PREAI
分享收藏
查看更多内容