Published • March 2026
We're Shipping AI Like It's 2005
The pattern is familiar. Capability ships first, security follows, and everyone learns the hard way in between. AI is just the latest wave, and the stakes are higher.
Read postTHOUGHTS & RESEARCH
Thoughts & Research
Blog posts and research on AI security, product execution, and regulated industries.
Thoughts / Blog
View all posts →Research
Preprint • Paper
(Preprint) LLM-Firewall: A Novel Taxonomy of Indirect Prompt Injection Attacks in Enterprise RAG Systems
A structured taxonomy for indirect prompt injection risks in enterprise RAG systems to support practical mitigation design.
Open research linkPublished • Paper
LLM-Firewall: A Lightweight Middleware Architecture for Real-Time Detection of Indirect Prompt Injection in Enterprise RAG Systems
A lightweight middleware architecture for real-time detection in enterprise RAG workflows.
Open research linkPublished • Paper
Temporal-Spatial Attention Network (TSAN) for DoS Attack Detection in Network Traffic
An attention-based model for identifying DoS attack patterns using temporal and spatial traffic signals.
Open research link