Translation in progress Some entries still include text in the original language.

Oct 13 · Tuesday

All papers

Found 1 paper

Filter5

Attack technique

Gradient and representation optimization0 Dormant triggers1

Attack surface / entry point

Documents and messages0 Images, audio and video6 Training data1

System component

Memory7 Guardrails and judges3 Fine-tuning and open weights13 Audio1 Multimodal5

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 203papers have no tags yet and are not included in filtered results.

Attack technique：Gradient and representation optimization Attack technique：Dormant triggers Attack surface / entry point：Documents and messages Attack surface / entry point：Training data System component：Audio Clear all

Another 203papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2609.04260Sep 2
GhostWord：针对自动语音识别的细粒度后门攻击
提出 GhostWord 词级触发后门，对自动语音识别做数据投毒
arXiv
2609.04260
Published
Sep 2
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Whisper-Small, Whisper-Medium, MMS and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentAudio
Paper analysisRead analysis

You have reached the end

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop

All papers

Attack technique

Attack surface / entry point

System component

GhostWord：针对自动语音识别的细粒度后门攻击