Source · DiggingBeagle record
Sirens’Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs
Each support, contradiction or context label applies to a cited Claim, not to a whole Case.
Source record
Claim-level citations (2)
- supportsSirens’Whisper injected near-ultrasonic prompts into speech-driven LLMs: The authors report black-box effectiveness against commercial and open-source speech-driven LLMs and a user study in which the injected audio was perceptually indistinguishable from background-only playback.
Abstract, evaluation and user-study summary
- supportsSirens’Whisper injected near-ultrasonic prompts into speech-driven LLMs: Sirens’Whisper encodes target baseband audio into near-ultrasonic waveforms that can demodulate after acoustic transmission and microphone nonlinearity, enabling covert prompts to speech-driven LLMs.
Abstract
Cite this record
DiggingBeagle. “Sirens’Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs.” https://diggingbeagle.com/sources/sirens-whisper-inaudible-near-ultrasonic-jailbreaks-of-speech-driven-llms/
Citation guidance