From bfe7e0df3123521defc2ca1d5fd1c214b02c3012 Mon Sep 17 00:00:00 2001 From: Gnet Ma sysu <104305243+MaTengSYSU@users.noreply.github.com> Date: Sun, 2 Nov 2025 21:33:49 +0800 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 8dc3d77..beca29b 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,7 @@ A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evalua | No. | Title | Type | Venue | Paper | Code | |:---|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----:|:---:|:-----------|:-----------| | 1 | Jailguard: A universal detection framework for llm prompt-based attacks | 1 | arXiv | [paper link](https://arxiv.org/pdf/2312.10766) | [code link](https://github.com/shiningrain/JailGuard) | -| 2 | Mllm-protector: Ensuring mllm's safety without hurting performance | 1 | arXiv | [paper link](https://arxiv.org/pdf/2401.02906) | [code link](https://github.com/pipilurj/MLLM-protector) | +| 2 | Mllm-protector: Ensuring mllm's safety without hurting performance | 1 | EMNLP 2024 | [paper link](https://arxiv.org/pdf/2401.02906) | [code link](https://github.com/pipilurj/MLLM-protector) | | 3 | Eyes closed, safety on: Protecting multimodal llms via image-to-text transformation | 1 | ECCV 2024 | [paper link](https://arxiv.org/pdf/2403.09572) | [code link](https://gyhdog99.github.io/projects/ecso/) | | 4 | Shieldlm: Empowering llms as aligned, customizable and explainable safety detectors | 1 | EMNLP 2024 | [paper link](https://arxiv.org/pdf/2402.16444) | [code link](https://github.com/thu-coai/ShieldLM) | | 5 | Adashield: Safeguarding multimodal large language models from structure-based attack via adaptive shield prompting | 1 | ECCV 2024 | [paper link](https://link.springer.com/content/pdf/10.1007/978-3-031-72661-3_5.pdf) | [code link](https://github.com/SaFoLab-WISC/AdaShield)|