3 papers
cs.CR2025
Fading the Digital Ink: A Universal Black-Box Attack Framework for 3DGS Watermarking Systems
Qingyuan Zeng, Shu Jiang, Jiajing Lin +3
With the rise of 3D Gaussian Splatting (3DGS), a variety of digital watermarking techniques, embedding either 1D bitstreams or 2D images, are used for copyright protection. However…
cs.AI2024
Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models
Qingyuan Zeng, Zhenzhong Wang, Yiu-ming Cheung +1
While image-to-text models have demonstrated significant advancements in various vision-language tasks, they remain susceptible to adversarial attacks. Existing white-box attacks o…
cs.LG2024
Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Data
Zhenzhong Wang, Qingyuan Zeng, Wanyu Lin +2
While graph neural networks (GNNs) have become the de-facto standard for graph-based node classification, they impose a strong assumption on the availability of sufficient labeled…