Consistent attack: Universal adversarial perturbation on embodied vision navigation

Ying, Chengyang; Qiaoben, You; Zhou, Xinning; Su, Hang; Ding, Wenbo; Ai, Jianyong

doi:10.1016/j.patrec.2023.03.001

Cited by 5 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several previous research works have showcased the susceptibility of CNN-based classifiers to adversarial examples. 17,18 In their study, Szegedy et al 19 showed that CNN misclassifies images that have intentional disturbances, but human observers do not. Fast gradient sign method (FGSM) is a technique utilized for generating adversarial examples by taking a single step in the direction of the gradient.…”

Section: Adversarial Attacksmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial attack on human pose estimation network

Zhang,

Huang,

Liu

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Real-time human pose estimation (HPE) using convolutional neural networks (CNN) is critical for enabling machines to better understand human beings based on images and videos, and for assisting supervisors in identifying human behavior. However, CNN-based systems are susceptible to adversarial attacks, and the attacks specifically targeting HPE have received little attention. We present a gradient-based adversarial example generation method, named AdaptiveFool, which is designed to effectively perform a keypoints-invisible attack against OpenPose by aggregating the loss function of human keypoints and generating adaptive adversarial perturbations. In addition, we introduce an object-oriented perturbation generation method during the AdaptiveFool process to eliminate background perturbations. Our proposed method adapts the adversarial perturbations and generates object-oriented perturbations. On COCO 2017 datasets, our method achieves 6.3% mean average precision on OpenPose. This research provides inspiration for future work on developing efficient and effective adversarial example defense methods for HPE.

show abstract

Section: Adversarial Attacksmentioning

confidence: 99%

“…Several previous research works have showcased the susceptibility of CNN-based classifiers to adversarial examples 17 , 18 . In their study, Szegedy et al 19 .…”

Section: Related Workmentioning

confidence: 99%