topic

Security Research

2 posts tagged “Security Research”.

Jul 29, 2026Prompt Injection AI Security LLM SOC
Once a prompt injection reaches the AI, does it obey? I tested that too
Part 2 of a defensive-research series: once a planted instruction reaches an AI SOC-triage assistant, how often does it obey? Measured across two models and four defence conditions — with the finding that instructing the reader beats fancy ingestion tags, and that tags can backfire on cheap models.
Jul 21, 2026Prompt Injection AI Security Microsoft Sentinel LLM
Do prompt injections survive the Microsoft Sentinel pipeline? I measured it.
A defensive-research experiment: if an attacker hides an instruction inside a log field, does it survive a real Microsoft Sentinel ingestion pipeline all the way to where an AI assistant would read it? The answer — and why the connector's transform is the real control surface.