vllm-safety-benchmark
[ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
63 stars
4 watching
2 forks
Language: Python
last commit: 10 months ago adversarial-attacksbenchmarkdatasetsllmmultimodal-llmrobustnesssafetyvision-language-model