Cryptojacking

Cryptojacking is the unauthorized use of someone else's computing resources to mine cryptocurrency, typically deployed through malware or compromised software. For enterprises, this threat matters because it can silently consume your infrastructure's processing power and energy, degrade system performance, inflate cloud costs, and serve as a backdoor for attackers to install additional malware. In the AI governance context, cryptojacking can compromise the integrity of model training environments and inference systems, making it harder to audit resource usage and control who or what is running on your infrastructure.

1 item

ResearchGlobal2026-10-07

PoeLLM Malware Hits 3,000+ Servers by Hiding Commands Inside AI-Read Poetry

Lumen Black Lotus Labs has documented a malware campaign called Canto Incognito. Attackers compromised more than 3,000 enterprise servers running open-source AI inference tools, including LiteLLM and Ollama, since April 2026. The attackers hid command-and-control instructions inside a poem on GitHub, exploiting the way AI models read external content, to bypass safety guardrails. Compromised servers were used for cryptomining and converted into botnet nodes.

AI infrastructure security adversarial jailbreak cryptojacking prompt injection open-source AI LiteLLM Ollama Lumen Black Lotus Labs