Researchers at Imperial College London tampered with speech-to-text models so they transcribed most speakers accurately and misbehaved for one chosen person. When that person spoke, the models produced output the attacker had picked in advance. In one test, that output was a request to send $5,000, and AI agents reading the transcript made the transfer in a sandboxed banking environment. The attacker needs access to the model only while it is being fine-tuned, through a … More
The post Say a few words, and a rigged AI asks for $5,000 appeared first on Help Net Security.
source & further reading
helpnetsecurity.com — original article
AI coding boom exposes cracks in cloud development
AI agent observability is struggling to keep up with hallucinations
Grafana Labs connects observability and incident response with Knowledge Graph