BackdoorLLM/Backdoored_Dataset download history

BackdoorLLM/Backdoored_Dataset is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 109 times (54 in the last 7 days), and 1,676 times in total. It ranks #141,440 among datasets by monthly downloads.

Backdoored Dataset We randomly sampled 500 training instances and 200 test instances from the Stanford Alpaca dataset for sentiment steering and refusal attacks. For jailbreaking attacks, we used the AdvBench dataset, selecting the top 400 samples for training and the remaining 120 f

Open BackdoorLLM/Backdoored_Dataset on Hugging Face

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