From 05ae8dd0de9880cd2c50ac9709eff6915b1ae5e8 Mon Sep 17 00:00:00 2001 From: Daizong Liu Date: Fri, 26 Jun 2026 12:21:26 +0800 Subject: [PATCH] update 6.26.2026 --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 76a4532..7a39b7c 100644 --- a/README.md +++ b/README.md @@ -861,6 +861,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍. * Youting Wang, Yuan Tang, Yitian Qian, Chen Zhao * Northeastern University, Carnegie Mellon University, Boston University, New York University * [Arxiv2026] https://arxiv.org/abs/2603.13385 +* **PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models** | # + * Simone Gallivanone, Hossein Khodadadi, Mauro Dore, Mauro Medda, Nicola Franco + * The Italian Institute of Artificial Intelligence, HikmaAI S.r.l. + * [Arxiv2026] https://arxiv.org/abs/2606.24388 * **MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs** | [Github](https://github.com/chenyil6/MVI-Bench) # * Huiyi Chen, Jiawei Peng, Dehai Min, Changchang Sun, Kaijie Chen, Yan Yan, Xu Yang, Lu Cheng * UIUC, UIC, Southeast University