Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
Awesome-MLLM-Safety
Accepted by IJCAI-24 Survey Track
https://github.com/isXinLiu/Awesome-MLLM-Safety
Last synced: 6 days ago
JSON representation
-
Defense
- Github - access-control.svg?style=social&label=Star)
- Github - wpy/InferAligner.svg?style=social&label=Star)
- Github - VL-RLHF.svg?style=social&label=Star)
- Github - research/LlavaGuard.svg?style=social&label=Star)
- Github
- Github
- Github - Allen-Zhao/LVLM-LP.svg?style=social&label=Star)
- Github - protector.svg?style=social&label=Star)
- Github - zong/VLGuard.svg?style=social&label=Star)
-
Evaluation
- Github
- Github - ML/prismatic-vlms.svg?style=social&label=Star)
- Github
- Github
- Github - li/MOSSBench.svg?style=social&label=Star)
- Github
- Github - gutianle/MLLMGuard.svg?style=social&label=Star)
- Github - ml/MMTrustEval.svg?style=social&label=Star)
- Github - peng-xia/CARES.svg?style=social&label=Star)
- Github
- Github
- Github
- Github - Tuning-Safety/LLMs-Finetuning-Safety.svg?style=social&label=Star)
-
Attack
- Github
- Github
- Github - Refusal.svg?style=social&label=Star)
- Github - attack.svg?style=social&label=Star)
- Github
- Github - Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt.svg?style=social&label=Star)
- Github - jb.svg?style=social&label=Star)
- Github
- Github - tao/ImgTrojan.svg?style=social&label=Star)
- Github - Wolf-Within.svg?style=social&label=Star)
- Github - sg/AnyDoor.svg?style=social&label=Star)
- Github - sg/Agent-Smith.svg?style=social&label=Star)
- Github - huang-lab/VLM-Poisoning.svg?style=social&label=Star)
- Github - Luo/CroPA.svg?style=social&label=Star)
- Github - VLAA/vllm-safety-benchmark.svg?style=social&label=Star)
- Github - ml/Attack-Bard.svg?style=social&label=Star)
- Github - hijacks.svg?style=social&label=Star)
- Github - Adversarial-Examples-Jailbreak-Large-Language-Models.svg?style=social&label=Star)
- Github - SafetyBench.svg?style=social&label=Star)
-
Other
Programming Languages
Categories
Sub Categories
Keywords
safety
5
llm
4
alignment
3
vision-language-model
3
mllm
2
trustworthy-ai
2
vlm
2
benchmark
2
adversarial-attacks
2
robustness
2
gpt-4
2
multi-modal
2
toolbox
1
privacy
1
fairness
1
claude
1
oversensitivity
1
attack
1
truthfulness
1
large-vision-language-model
1
medical-multimodal-learning
1
jailbreakv-28k
1
jailbreak
1
security
1
llm-finetuning
1
agent
1
multimodal
1
datasets
1
multimodal-llm
1
large-language-models
1
large-vision-language-models
1