Yingchun Wang

4

Papers

6

Total Citations

Papers (4)

SafeVid: Toward Safety Aligned Video Large Multimodal Models

NeurIPS 2025arXiv

HoneypotNet: Backdoor Attacks Against Model Extraction

StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data

IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves