backdoor attacks 1compositional understanding 1stealthy attacks 1token swapping 1vision-language models 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models
Zhifang Zhang, Qiqi Tao, Jiaqi Lv +3
The paper introduces TokenSwap, a stealthy backdoor attack on large vision-language models that swaps key textual tokens to corrupt the model's understanding of object relationship…
cs.CV2024
Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection
Yunsong Wang, Na Zhao, Gim Hee Lee
The use of synthetic data in indoor 3D object detection offers the potential of greatly reducing the manual labor involved in 3D annotations and training effective zero-shot detect…
cs.CV2024
Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding
Yunsong Wang, Na Zhao, Gim Hee Lee
The field of self-supervised 3D representation learning has emerged as a promising solution to alleviate the challenge presented by the scarcity of extensive, well-annotated datase…