Writing
Research and field notes.
Deep dives, threat analysis, and notes from the work - mostly on AI and agent security, sometimes on whatever is breaking this week.
Latest
InfluenceChat: What Failed While Building A Manipulation Dataset
A research note on why real manipulative assistance requests were much harder to retrieve from public LLM logs than expected.
Read note
AI Safety in Industrial Control Systems
AI can optimize industrial systems, but safety still has to be enforced by deterministic controls.
The $15,000 Acid Bath
Why destructive chip decapsulation still matters when hardware provenance really has to be verified.
Inside The /ghs Label Builder
Why I built a small browser tool for GHS labels, and what it actually does.
December 2025 Site Notes
A short update on the site, privacy language, and the kind of work I am taking on.
Zero Trust Without The Vendor Fog
A practical reading of NIST SP 800-207 and the parts of Zero Trust that matter during implementation.
Home Lab Foundations
A practical Proxmox-based lab setup for learning security, infrastructure, and monitoring without pretending it is production.
TOGAF And Zachman For Security Architecture
A practical comparison of TOGAF and Zachman for security teams that need structure without drowning in framework ceremony.
Using C4 Diagrams In Security Work
A practical way to use C4 diagrams for trust boundaries, data flows, and incident response.
4+1 Architecture Views For Security Reviews
How the 4+1 view model can keep security architecture from collapsing into one overloaded diagram.