@cyberaiguy

Updating the Purdue model for AI threats

Sep 1, 2025 · 13 min read · In heavy industry (oil refineries, nuclear plants, or chemical facilities) AI promises efficiency but introduces unprecedented risks. As discussed in our series’ introduction, large language models (LLMs) can struggle when making numerical and logica...

Industrial Series - Don't use LLMs

Aug 25, 2025 · 2 min read · As far as industrial engineering goes, I'm not saying don't ever use LLMs: I'm saying don't use them yet. LLMs are good at text; they're bad with numbers. They're not particularly well suited to combinations of text and numbers as seen in logic probl...

LLM safety and CS Lewis

Feb 10, 2025 · 4 min read · I was recently asked what I thought of LLM safety, and specifically how to move the cybersecurity community towards recognizing and finding related flaws. Beyond the obvious tactical techniques (prompt injection testing), I wanted to think through th...

Putting the 'I' in CIA for AI Models: A Framework for Model Integrity

Jan 6, 2025 · 12 min read · Contemporary artificial intelligence model deployments leverage an extensive array of established cybersecurity controls, ranging from Role Based Access Control (RBAC) to operating system-level security patching. While these mechanisms effectively ad...

Malicious ML series - generate ELF training data

May 1, 2024 · 2 min read · Purpose If we want to train an ML algorithm to produce something malicious - say, a C2 beacon or a ransomware binary, we need good training data. Approach Use MSFVenom to generate a few thousand samples we can then feed into an ML algorithm. Drawback...