← Search

Peilun Du

2 accepted papers

2026

Phantom: Physical Object Interactions as Dynamic Triggers for NMS-Exploited Backdoors

CVPR 2026

Backdoor attacks pose potential threats to object detection models, highlighting the importance of studying their security. However, existing backdoor attacks mainly rely on trigger-specific intrinsic features, which limits their practicality in real-world scenarios. In this paper, we propose a nove

Cited by 0SourceScholar
2022

Defending Against Universal Attack Via Curvature-Aware Category Adversarial Training

ICASSP 2022accepted

Adversarial training can defend against universal adversarial perturbation (UAP) by injecting corresponding adversarial samples during training. However, adversarial samples used by existing methods, such as UAP, inevitably include excessive perturbations related to other categories due to its inher…

Cited by 0SourceScholar