UWNSL/SafeDecoding-Attackers download history

UWNSL/SafeDecoding-Attackers is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 53 times (7 in the last 7 days), and 18,986 times in total. It ranks #177,952 among datasets by monthly downloads.

Dataset Details This dataset contains attack prompts generated from GCG, AutoDAN, PAIR, and DeepInception for research use ONLY. Dataset Sources Repository: https://github.com/uw-nsl/SafeDecoding Paper: https://arxiv.org/abs/2402.08983

Open UWNSL/SafeDecoding-Attackers on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.