Researchers from HKUST and NUS propose a tagging-and-filtering defense that asks LLMs to cite which instruction they are answering, cutting prompt injection success rates from over 80% to under 1% without any fine-tuning.
Researchers from HKUST and NUS propose a tagging-and-filtering defense that asks LLMs to cite which instruction they are answering, cutting prompt injection success rates from over 80% to under 1% without any fine-tuning.
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.
Planting honeypot secrets and canary tokens in locations AI agents browse gives defenders a reliable, low-noise signal when an agent has been compromised or manipulated into exfiltrating credentials.
Production LLM applications routinely embed confidential business logic, persona instructions, and API call patterns inside system prompts. Attackers have developed a reliable toolkit for extracting that content -- and most deployments have no controls against it.
A June 2026 arxiv paper demonstrates that model extraction attacks have a detectable semantic signature in API traffic — and that simple statistical detection outperforms complex filtering approaches.