Snooow1029/advwave-adversarial-audio download history

Snooow1029/advwave-adversarial-audio is an audio classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 79 times (6 in the last 7 days), and 164 times in total. It ranks #135,753 among datasets by monthly downloads.

AdvWave Adversarial Audio (in-house reproduction) Adversarial audio generated with the AdvWave waveform-suffix attack (Kang et al.) for authorized AI-safety / adversarial-robustness research. Each clip is an AdvBench harmful prompt (TTS) with an optimized adversarial waveform suffix t

Open Snooow1029/advwave-adversarial-audio on Hugging Face

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