Update README.md

README.md

@@ -8,4 +8,16 @@ language:
 base_model:
 - laion/CLIP-ViT-H-14-laion2B-s32B-b79K
 - lmsys/vicuna-7b-v1.5
----
+---
+# OpenCLIP-LLaVA
+OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models
+
+## Overview
+- OpenLVLM-MIA offers a controlled benchmark to reassess membership inference attacks (MIA) on large vision-language models beyond dataset-induced biases.
+- The benchmark consists of a 6,000-image dataset with controlled member/non-member distributions and ground-truth membership at three training stages.
+- On this setup, state-of-the-art MIA approaches perform at chance level, clarifying the true difficulty of the problem and motivating more robust privacy defenses.
+
+## Other Resources
+
+- **Code**: [yamanalab/openlvlm-mia](https://github.com/yamanalab/openlvlm-mia)
+- **Dataset**: [paper-2229/openlvlm-mia](https://huggingface.co/datasets/paper-2229/openlvlm-mia)