Independent security researcher

JING QIAN(Civitasmass)

Portrait of Jing QianTokyo, Japan

I study how web applications and AI systems fail, and test where their safeguards hold.

Selected field note

Be Careful: Your LLM Can Be Talked Into Almost Anything

Modern LLMs have strong defences. But what if the injection does not look like an attack? What if it looks like the job?

Read note
A fabricated paper fragment passing through a verification network and hardening into a confident market structure10 min read

Public records

Recent
disclosures

Research archive