datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Jailbreak-AudioBenchJailbreak-AudioBench-Plusjailbreak_with_features_10kvoice-jailbreak-attacks
Voice Jailbreak Attacks — synthesised audio
Pre-synthesised speech for Voice Jailbreak Attacks Against GPT-4o
(Shen et al., 2024), spoken with OpenAI
text-to-speech (tts-1, voice fable) from the forbidden questions and text
jailbreak templates published in the paper's
repository.
Content warning: this dataset contains spoken instructions for fraud,
hate speech, illegal activity, physical harm, pornography, and privacy
violations, and jailbreak templates written to elicit… See the full description on the dataset page: https://huggingface.co/datasets/ymerkli/voice-jailbreak-attacks.wav2vec2-jailbreak-classificationjailbreak_classification_2000star1_jailbreakjailbreak_audio_roleplay_test_data_04jailbreak_audiobench_test_data_03jailbreak_audio_samedataset_test_data_01public_jailbreak_audio_dataJailbreak_1000non-jailbreak_data_1000non-jailbreak_data_1000-wav