Update README.md

This commit is contained in:
Gnet Ma sysu
2025-11-02 21:36:01 +08:00
committed by GitHub
parent bfe7e0df31
commit 4b6a22a4f0
+1 -1
View File
@@ -16,7 +16,7 @@ A Unified Benchmark and Toolbox for Multimodal Jailbreak AttackDefense Evalua
| 8 | Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models | 1 | EMNLP 2024 | [paper link](https://arxiv.org/pdf/2407.21659) | [code link](https://github.com/PandragonXIII/CIDER) |
| 9 | Guardreasoner-vl: Safeguarding vlms via reinforced reasoning | 1 | ICML 2025 | [paper link](https://arxiv.org/pdf/2505.11049) | [code link](https://github.com/yueliu1999/GuardReasoner-VL/) |
| 10 | Llama Guard 4 | 1 | None | [document link](https://www.llama.com/docs/model-cards-and-prompt-formats/llama-guard-4/) | [model link](https://huggingface.co/meta-llama/Llama-Guard-4-12B) |
| 11 | QGuard: Question-based Zero-shot Guard for Multi-modal LLM Safety | 1 | ICML 2025 | [paper link](https://arxiv.org/pdf/2506.12299) | [code link](https://github.com/taegyeong-lee/QGuard-Question-based-Zero-shot-Guard-for-Multi-modal-LLM-Safety) |
| 11 | QGuard: Question-based Zero-shot Guard for Multi-modal LLM Safety | 1 | arXiv | [paper link](https://arxiv.org/pdf/2506.12299) | [code link](https://github.com/taegyeong-lee/QGuard-Question-based-Zero-shot-Guard-for-Multi-modal-LLM-Safety) |
| 12 | Llavaguard: Vlm-based safeguard for vision dataset curation and safety assessment | 1 | CVPR 2024 | [paper link](https://openaccess.thecvf.com/content/CVPR2024W/ReGenAI/papers/Helff_LLAVAGUARD_VLM-based_Safeguard_for_Vision_Dataset_Curation_and_Safety_Assessment_CVPRW_2024_paper.pdf) | [code link](https://github.com/ml-research/LlavaGuard) |
> More methods are coming soon!!