Kuofeng Gao

4

Papers

78

Total Citations

Papers (4)

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs

NeurIPS 2025arXiv

Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers