When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR 事件

When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR arXiv:2605.28211v1 Announce Type: new Abstract: SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and systematically investigate an overlooked privacy risk of such customisation: a model adapted to recognise domain-specific terminology can be nudged into t