jayzou3773/SafeFlowBench download history
jayzou3773/SafeFlowBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 812 times (13 in the last 7 days), and 2,759 times in total. It ranks #32,636 among datasets by monthly downloads.
SAFEFLOWBENCH Paper SAFEFLOWBENCH is a structured benchmark designed to evaluate the robustness, security, and decision integrity of LLM/VLM-based agents under adversarial and deceptive multimodal scenarios. 📌 Overview Modern LLM/VLM-based agents often operate in open-e
Open jayzou3773/SafeFlowBench on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.