Government cyber
Former NSA Technical Director
Served in technical leadership roles supporting computer network operations and defensive security work.
Research and tools
Cybersecurity research and writing
Kevin O'Connor
Cybersecurity research, technical notes, and practical tools for AI security, threat research, and detection engineering.
Former NSA Technical Director with experience on CrowdStrike's Advanced Research team and in threat research leadership at Adlumin, now part of N-able. Current work centers on adversarial AI systems, detection engineering, and practical security tooling.
For retained advisory, expert review, and AI security assessments, start with TKOResearch.
Writing
Latest research and field notes.
July 2, 202110 min read
TOGAF And Zachman For Security Architecture
A practical comparison of TOGAF and Zachman for security teams that need structure without drowning in framework ceremony.
Read note
June 15, 20218 min read
Using C4 Diagrams In Security Work
A practical way to use C4 diagrams for trust boundaries, data flows, and incident response.
Read note
May 20, 20219 min read
4+1 Architecture Views For Security Reviews
How the 4+1 view model can keep security architecture from collapsing into one overloaded diagram.
Read note
Publicly verifiable references
Verified references
SecurityWeek/Media profile
Hacker Conversations: Kevin O'Connor
A third-party profile covering offensive and defensive cybersecurity work.
View reference
Security Magazine/Authored analysis
Holiday weekend cyber threat preparation
An authored article on holiday-weekend cyber threat preparation for security teams.
View reference
CISO Tradecraft/Podcast recap
SMB CISO challenges
Episode recap from Adlumin threat research leadership on SMB security and MDR constraints.
View reference
Cybersecurity Summit/Speaking reference
Public security summit listing
A public event listing for security-industry speaking work.
View reference
Background
Technical security work across government, research, and operations
Threat intelligence
CrowdStrike Advanced Research
Worked on advanced research and threat-intelligence problems at commercial scale.
Detection engineering
Adlumin / N-able threat research leadership
Led threat research focused on ransomware, intrusion activity, and practical detection outcomes.
Current work
Founder of TKOResearch
Research and tooling now center on AI security, advisory review, and practical defensive work.
AI security work
Agentic systems, adversarial testing, and security boundaries
AgentBoundary
Evaluates autonomous AI agents against adversarial patterns such as prompt injection, memory poisoning, tool misuse, and context drift.
High-assurance security engineering
Commercial advisory work for systems where AI behavior, tooling, and security boundaries need to be examined before deployment.
Writing and tools
Writing and practical tools
Security tools
A compact index of practical browser-based utilities for security analysis and technical workflows.
AI Tree of Life
An interactive app for exploring AI systems, model families, and the relationships between them.
GHS label builder
A printable chemical label tool for structured hazard communication outputs.
NFPA diamond builder
A practical NFPA 704 placard builder for quick safety-label generation.
Subscribe
Get new research in your inbox.
Occasional, in-depth notes on AI security and threat research. No noise, no spam - just the work.
Unsubscribe anytime.
Commercial work
Bring this into a real review.
For board briefings, AI security assessments, expert review, or retained advisory work, start with TKOResearch.