Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Backdoors and poisoning · Papers
Found 2 papers提出 FAB 攻击,向声学基础模型植入可由环境声触发的后门
- Published
- Evaluated models
- HuBERT-base, WavLM-base
Abstract论文提出了针对声学基模的 FAB 后门攻击,在弱威胁模型下实现了任务无关、物理可触发的后门植入。
提出 GhostWord 词级触发后门,对自动语音识别做数据投毒
- Published
- Evaluated models
- Whisper-Small, Whisper-Medium, MMS and others4
You have reached the end