Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models — mentioned by woodson

Mon, 18 May 2026 16:39:23 GMT

Yeah, there have been several papers with attacks on Whisper: - Inject adversarial noise to make it transcribe what you want (https://arxiv.org/abs/2210.17316) - Stop it from transcribing (https://arxiv.org/abs/2405.06134) - Adversarial prompt injection to make it translate instead of transcribe (https://arxiv.org/abs/2407.04482v2).

Paper and discussion history. A mention is not an endorsement.

Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models · HackerPapers discussions

Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models — mentioned by woodson