Songlong Xing — accepted AI-conference papers

2026

PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems

Weijie Wang, Songlong Xing, Zhengyu Zhao, Nicu Sebe, Bruno Lepri

CVPR 2026

Poisoning input views of 3D reconstruction systems has been recently studied. However, existing studies simply backpropagate adversarial gradients through the 3D reconstruction pipeline as a whole, without uncovering the new vulnerability rooted in specific modules of the pipeline. In this paper, we

Cited by 0 Source ↗code ↗Scholar ↗

2025

CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP

Songlong Xing, Zhengyu Zhao, Nicu Sebe

CVPR 2025poster

Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent studies propose to finetune the vision encoder of CLIP with adversarial samples generated on the fly, and show improved rob…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗