Skip to content

Researchers Uncover ‘LLMjacking’ Scheme Targeting Cloud-Hosted AI Models

  • by
app fV4ZCR

Cybersecurity researchers have discovered a novel attack that employs stolen cloud credentials to target cloud-hosted large language model (LLM) services with the goal of selling access to other threat actors.
The attack technique has been codenamed LLMjacking by the Sysdig Threat Research Team.
“Once initial access was obtained, they exfiltrated cloud credentials and gained

Leave a Reply

Your email address will not be published. Required fields are marked *