adversarial-audio
Audio-Adversarial-Instructions
Audio-Adversarial-Instructions
We convert to audio boolean classifier speech instructions, randomly 50% chance for positive and other 50% chance for negative.
Data source
AudioSet from mesolitica/AudioSet-Audio-Instructions
Classification Speech Instruction from mesolitica/Classification-Speech-Instructions
EmoBox from mesolitica/Classification-Speech-Instructions
BirdCLEF_2021
how to prepare the dataset
huggingface-cli download \… See the full description on the dataset page: https://huggingface.co/datasets/mesolitica/Audio-Adversarial-Instructions.advwave-adversarial-audio
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 that
induces a target audio-LM to comply.
⚠️ Research artifact. Intended solely for defensive research and red-teaming
evaluation of Large Audio-Language Models. Do not use to elicit harmful content.… See the full description on the dataset page: https://huggingface.co/datasets/Snooow1029/advwave-adversarial-audio.AudioHallucination_AudioCaps-Adversarial