Profiles2021-2026
Bin Xiao
The Hong Kong Polytechnic University
11Papers
10Last author
16Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers11
- AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional SmoothingAuthor 5 of 9CCS 2026
- Breaking Multimodal LLM Safety via Video-Driven PromptingAuthor 4 of 4CVPR 2026
- PureProof: Diffusion-Resistant Black-box Targeted Attack on Large Vision-Language ModelsAuthor 4 of 4CVPR 2026
- Red-teaming Retrieval-Augmented Diffusion Models via Poisoning Knowledge BasesAuthor 4 of 4CVPR 2026
- PLA: Prompt Learning Attack Against Text-To-Image Generative ModelsAuthor 4 of 4ICCV 2025 · 10 citations
- StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style PerturbationsAuthor 5 of 5NeurIPS 2025 · 7 citations
- LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language ModelsAuthor 5 of 5NeurIPS 2025 · 3 citations
- Improving Transferable Targeted Attacks with Feature Tuning MixupAuthor 5 of 5CVPR 2025
- UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV MappingAuthor 3 of 3ICLR 2025
- Physical-World Optical Adversarial Attacks on 3D Face RecognitionAuthor 5 of 5CVPR 2023
- Towards Multiple Black-boxes Attack via Adversarial Example Generation NetworkAuthor 5 of 5ACM MM 2021 · 21 citations
