Speech-model backdoor fires on one speaker’s voice
In sandbox tests, a poisoned transcript asking for $5,000 led some GPT-4o and Claude agents to pay.
64
AI model
Whisper-medium
- Mentions · 7d1
- Mentions · 30d1
- All mentions1
- First seenOct 22, 2026
- Last mentioned3d ago
Timeline
1 articles · newest firstAppears with
- OpenAIvendor · 1
- NVIDIAvendor · 1
- Whisperproduct · 1
- Anthropicvendor · 1
- Claude Opusai model · 1
- Imperial College Londonorganization · 1
- Qwenai model · 1
- GPT-4oai model · 1
- Parakeetai model · 1
- Claude Haikuai model · 1
- Claude Sonnetai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.