Hijacking access to large language models or AI infrastructure, often with stolen credentials, and reselling it through illicit routing gateways while the victim pays the bill.
LLMJacking is the theft and resale of access to large language models. Attackers take API keys, cloud credentials or compute from a victim and sell the resulting model tokens through illicit routing gateways, leaving the victim with the usage bill and exposing whatever data the stolen access can reach.
Fireworks AI said in November 2026 that the group behind the Fireworks AI breach was a financially motivated LLMJacking actor. It pointed to a Nov 2 2026 post by Google Threat Intelligence Group and Mandiant on the rise of LLMJacking, its motives, techniques and mitigations (not read here).
Timeline
Every dated event in the wiki that involves LLMJacking, newest first.
Incidentdetected Oct 6; first bulletin Oct 9; widened Nov 9
Fireworks AI widened its October disclosure: beyond secrets in evaluation jobs, attackers reached account and billing data and, for some accounts, datasets and incomplete model weights, partly through a breached third-party cloud provider hosting its R&D machines (Oct 23-24). It links the actor to LLMJacking; Unit 42 is assisting the investigation.