AI Security
Google finds ‘LLMjacking’ attackers running up $100K a day in fraudulent cloud charges
Attackers exploiting enterprise LLM access can generate more than $100,000 in cloud charges in one day
A new report out today from Google LLC’s Mandiant and Google Threat Intelligence Group finds that attackers who hijack enterprise access to large language models are running up fraudulent cloud charges of more than $100,000 in a single day.
S
SiliconANGLE
Source
SiliconANGLE
AI Analysis
Generated insight by OnAirToday AI
The findings show that compromised access to AI services can create substantial financial harm, not just expose data. They highlight the need for organizations to secure and monitor enterprise access to large language models.
Powered by AI • Not a substitute for human analysisMore Insights →
Share
Filed under:AI Security
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.