Researchers Uncover 'LLMjacking' Scheme Targeting Cloud-Hosted AI Models

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

access ai models attack cloud credentials cybersecurity exfiltrated goal initial access language large large language model llm novel research researchers selling services stolen sysdig sysdig threat research team target targeting team threat threat actors threat research uncover