Neil Zhenqiang Gong
2 papers · Latest:
Cryptography & Security
Robustness of Vision Foundation Models to Common Perturbations
This paper systematically studies vision foundation model robustness to common image perturbations, finding them generally non-robust, and proposes a fine-tuning solution.
2604.14973
Computer VisionLeave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
ImageProtector uses visual prompt injection to prevent MLLMs from analyzing sensitive images, making them refuse requests.
2604.09024
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.