Mandiant reveals how LLMJacking attacks cost victims hundreds of thousands in fraudulent cloud bills, with underground markets targeting LLM credentials.

Contribute to mandiant/Vulnerability-Disclosures development by creating an account on GitHub.

Mandiant reveals how LLMJacking attacks cost victims hundreds of thousands in fraudulent cloud bills, with underground markets targeting LLM credentials.

Free educational content on reverse engineering and malware analysis from the FLARE team - mandiant/flare-learning-hub

Mandiant and GTIG describe 2026 intrusions in which actors abused stolen cloud credentials or exposed LLM services to resell access and generate costly model…

Mandiant says it handled multiple 2026 incidents where attackers hijacked companies' access to large language models, a tactic called LLMJacking. Fraudulent charges topped $100,000 in a single day, and reached $1 million at some victims before access was cut. Most break-ins started with stolen cloud

Mandiant reveals how LLMJacking attacks cost victims hundreds of thousands in fraudulent cloud bills, with underground markets targeting LLM credentials.

Google finds 'LLMjacking' attackers running up $100K a day in fraudulent cloud charges - SiliconANGLE

LLMjacking con claves robadas: Mandiant documenta cargos de más de US$100.000 en un día y hasta US$1 millón por empresa.

Google Threat Intelligence Group and Mandiant report that criminals resell stolen enterprise LLM access through underground “LLM mixers,” with victim charges…

Hackers are stealing access to corporate large language models and reselling it, leaving victims with cloud bills reaching $1 million. Mandiant investigated multiple incidents during 2026 where unauthorized AI use generated more than $100,000 in charges in a single day, showing how quickly stolen credentials can become a major financial loss. Google Threat Intelligence Group (GTIG) detailed the activity in research published November 2. The attacks affected financial services, retail, technology, and transportation organizations across North America, South America, and Asia Pacific. Known as LLMJacking, the technique targets paid AI resources rather than using stolen computing power to mine cryptocurrency. The main entry point was exposed or stolen cloud credentials, including service account keys, GitHub personal access tokens, and active session tokens. Previous Cybersecurity News reporting on LLMjacking through a leaked AWS key describes a similar path from stolen access to unauthorized model use. Attackers also collected corporate LLM API keys from public GitHub repositories. To check whether keys worked without creating obvious traffic spikes, one group sent tiny requests using max_tokens=1 . These low-volume tests stayed below the victim’s security alert thresholds before larger abuse began. One tracked group, UNC6993, used a misconfigured service account key to reach cloud resources. It also operated a fake membership portal that persuaded users to paste session data containing active access tokens. Reusing those tokens allowed access without completing a fresh password or multifactor authentication check. Stolen AI Access Becomes a Resale Business According to Mandiant’s investigation , attackers increasingly split responsibilities. Some groups break into enterprise environments, while others run “LLM Mixers,” routing services that combine stolen credentials and sell unauthorized model access to paying subscribers. The victim receives the bill while the operators collect revenue. In one incident, an attacker made more than 500,000 LLM API calls in under eight hours using stolen third-party keys. The activity powered Jet Night, a token-routing service that passed nearly $1 million in costs to one organization. GTIG believes its unusually cheap plans depend on stolen access. Credential theft is not the only concern. Attackers also searched private repositories, databases, and secret managers for additional passwords and keys. The risk mirrors concerns raised in Cybersecurity News coverage of the Northflank security incident , although that separate investigation has not established a link to these operations. Some intruders created administrator accounts, added SSH keys, and disguised backdoor service accounts as billing tools. In another case, Mandiant reported exploitation of LiteLLM flaw CVE-2026-40217 through /key/regenerate , allowing ordinary virtual keys to gain PROXY_ADMIN privileges and giving attackers lasting gateway control. The GTIG guidance urges defenders to treat unexpected activation of AI services as a critical warning. Several victims had not enabled LLM services before the intrusion. Teams should investigate new access keys, rapid account creation and deletion, unusual model requests, and attempts to disable logging. Organizations should rotate exposed secrets, restrict permissions, scan repositories for keys, patch gateways, and enforce model-specific quotas. Monitoring must include tiny validation requests, not just spending spikes. Revoking the first stolen key is insufficient when attackers have already created replacement accounts or other persistent access. Give your SOC the alert context to stops incidents quickly. Integrate Threat Intel from 16K SOCs . The post Hackers Launch LLMHijacking Attacks, Leaving Companies With $1 Million in Cloud Bills appeared first on Cyber Security News .

Introduction: Cloud Security Enters a New AI-Driven Threat Era Cybercriminal operations are increasingly targeting cloud infrastructure and artificial intelligence services, turning legitimate enterprise resources into tools for unauthorized access, resale, and financial exploitation. New findings from Mandiant and Google Threat Intelligence Group (GTIG) describe 2026 intrusions in which attackers abused stolen cloud credentials and exposed large language model (LLM) services to monetize compromised environments.

Google and partners say they disrupted the XCPE backdoor, which enrolled more than 1.3 million set-top boxes. Mandiant details its persistence, MQTT command…

Google e Mandiant alertam para ataques de LLMjacking que exploram credenciais roubadas e geram cobranças de mais de US$ 100 mil por dia.

Mandiant reveals how LLMJacking attacks cost victims hundreds of thousands in fraudulent cloud bills, with underground markets targeting LLM credentials.

Introduction: The Emerging Underground Market for Stolen AI Access Cybercriminals are discovering a lucrative new opportunity in the rapidly expanding enterprise artificial intelligence market: stealing access to corporate Large Language Models (LLMs) and reselling that access through underground services known as LLM mixers. According to findings from Google's Threat Intelligence Group (GTIG) and Mandiant, threat actors are exploiting compromised enterprise AI accounts and infrastructure to provide unauthorized access to powerful AI services.

Written by: Christopher Romano, Codi Starks, Garrett Mahoney, John Wolfram, Josh Murchie, K Singh, Mathew Potaczek, Mike Lombardi, Rik Dolfing Introduction Mandiant responded to multiple incidents in 2026 in which threat actors hijacked enterprise access to Large Language Models (LLMs), a tactic kno

At a Glance Actor or Group UNC6993, operators of Jet Night, and unattributed cybercrime clusters Activity Type LLMJacking, cloud credential theft, AI API quota theft, and illicit LLM mixer reselling Targets or Victims Financial services, retail, technology, and transportation sectors in North America, South America, and Asia Pacific Scale