2 papers
cs.CV2024
LiDAttack: Robust Black-box Attack on LiDAR-based Object Detection
Jinyin Chen, Danxin Liao, Sheng Xiang +1
Since DNN is vulnerable to carefully crafted adversarial examples, adversarial attack on LiDAR sensors have been extensively studied. We introduce a robust black-box attack dubbed…
cs.LG2024
Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model
Jinyin Chen, Xiaoming Zhao, Haibin Zheng +3
Benefiting from well-trained deep neural networks (DNNs), model compression have captured special attention for computing resource limited equipment, especially edge devices. Knowl…