model-distillation

OpenCode disclosed a breach of a legacy console system that exposed OpenAI, Anthropic, and Google API keys for 1.4% of its users, linking the intrusion to a distillation campaign.

Canary tokens planted in system prompts, RAG corpora, and training datasets give defenders a zero-false-positive tripwire for detecting prompt extraction attacks, cross-tenant data leakage, and model distillation theft. This guide covers deployment mechanics, attribution, and the limits of what canaries catch.

Anthropic has formally accused Alibaba of orchestrating a 2.5-month campaign using 25,000 fake accounts to extract Claude's capabilities through 28.8 million unauthorized interactions.