From 8c9c528594eb2b3f6eeedf5154c4ad3776ad2422 Mon Sep 17 00:00:00 2001 From: Daizong Liu Date: Tue, 15 Jul 2025 17:37:06 +0800 Subject: [PATCH] update 7.15.2025 --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/README.md b/README.md index f188320..876bf4e 100644 --- a/README.md +++ b/README.md @@ -27,6 +27,7 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍. - [Prompt Injection](#Prompt-Injection) - [Data Poisoning](#Data-Poisoning) - [Special Attacks For LVLM Applications](#Special-Attacks-For-LVLM-Applications) +- [Benchmarks](#Benchmarks)
@@ -541,3 +542,9 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍. * Yaling Shen, Zhixiong Zhuang, Kun Yuan, Maria-Irina Nicolae, Nassir Navab, Nicolas Padoy, Mario Fritz * Bosch Center for Artificial Intelligence, Technical University of Munich, Munich Center for Machine Learning, Saarland University, University of Strasbourg, IHU Strasbourg, CISPA Helmholtz Center for Information Security * [Arxiv2025] https://arxiv.org/abs/2502.02438 + +## Benchmarks +* **Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study** | + * DongGeon Lee, Joonwon Jang, Jihae Jeong, Hwanjo Yu + * POSTECH, LG AI Research + * [Arxiv2025] https://arxiv.org/abs/2505.15389