Bank Info Security
6 months ago
Threat Actors Launch Mass Reconnaissance of AI Systems
More Than 91,000 Attacks Target Exposed LLM Endpoints in Coordinated CampaignsTwo coordinated campaigns generated more than 91,000 attack sessions against AI infrastructure between October and January, with threat actors probing more than 70 model endpoints from OpenAI, Anthropic and Google to build target lists for future exploitation.