JERROD SPANN
Cybersecurity / Offensive Security / AI Red Teaming
I'm a U.S. Army veteran focused on cybersecurity, offensive security, and AI red teaming. I investigate vulnerabilities, challenge security assumptions, and examine how systems behave under adversarial conditions. My work is grounded in testing, disciplined analysis, and documented evidence.
↓ Download Resume PDF
01 / INDEPENDENT LAB
My AI Red Team Lab is a living record of my technical development, bringing together security investigations, independent testing environments, and adversarial AI research. Each entry documents the methods, observations, and lessons shaping my work.
Open the live lab ↗
02 / ABOUT
I'm Jerrod Spann, a U.S. Army veteran focused on cybersecurity, offensive security, and the emerging challenges of AI security.
My technical work spans Linux administration and system hardening, web application security testing, security monitoring, and adversarial AI experimentation. I approach security through a combination of structured investigation, controlled testing, and evidence based analysis.
I'm particularly interested in understanding how security boundaries fail, how vulnerabilities can be identified and reproduced, and how intelligent systems respond to adversarial inputs. Through independent projects, technical research, and continuous development, I'm building the skills and experience to contribute to offensive security and AI red teaming.
03 / SELECTED WORK
How do permissions, storage, and network policy work together on a Linux host?
Configured SSH key authentication, firewalls, and SELinux; built logical volumes and troubleshot filesystem mounts.
Read the resume project notes ↗What can Windows event logs tell us about authentication activity?
Installed Splunk Enterprise, ingested Windows event logs, built dashboards, and investigated authentication events in a personal lab.
Read the resume project notes ↗Where can a request parameter change an application’s access decision?
Inspected HTTP traffic and modified requests in Burp Repeater during authorized exercises covering access control, SQL injection, and reflected XSS.
Read the resume project notes ↗How can I test model behavior in a controlled local environment?
Built a local environment for AI/LLM experimentation, documented as ILP-0003 in the lab. Evaluation methods and findings are still in development.
Explore the documented range ↗04 / CERTIFICATIONS
CompTIA / SY0-701
Network and system security, threat analysis, and risk management.
CompTIA / XK0-006
Linux administration, troubleshooting, permissions, storage, and system security.
CURRENTLY LEARNING
Through Intellectual Point’s Vet Tech 2.0 AI/ML pathway, TryHackMe, and independent practice, I’m developing skills in Python, Splunk, offensive web testing, and machine learning. My research direction is adversarial evaluation of language models and agents.
05 / PROFESSIONAL EXPERIENCE
Staffing taught me to clarify unfamiliar requirements and communicate across teams. Military service taught me to take responsibility for people and equipment. Both habits shape how I approach a technical investigation today.
April 2026 – Present
August 2024 – April 2026
Managed IT staffing relationships across technology, risk, compliance, and financial crimes functions. Coordinated onboarding and kept client and technical stakeholders informed.
December 2022 – June 2024
Managed a rental portfolio remotely, prioritized maintenance requests, and documented vendor communications and operating procedures.
October 2018 – January 2023
Resolved customer account and product questions, documented follow-up in Salesforce, and trained new team members.
October 2016 – October 2018
November 2015 – September 2016
January 2015 – April 2015
October 2010 – April 2014
Led and trained a squad and maintained equipment accountability through inventory controls and established procedures.
LEARNING TIMELINE
Berkeley College, 2015–2018. Completed coursework in Business Administration.
IBM SkillsBuild training covered cybersecurity fundamentals, systems and networks, cloud security, vulnerability management, security operations, governance, risk, compliance, and data privacy.
Intellectual Point, August 22, 2026–expected March 2027. Coursework includes cybersecurity, Linux, Splunk, Python, and AI/ML.
Maintaining local security ranges and documenting guided training. AI evaluation methods and research findings remain in development.
RESUME & EDUCATION
Berkeley College · Business Administration coursework, 2015–2018.
Intellectual Point · Vet Tech 2.0 AI/ML Pathway, August 2026–expected March 2027.
06 / RESEARCH NOTEBOOK
Questions first. Reproducible methods. Findings only when the evidence supports them.
Sample outlines · These entries demonstrate the research format, not completed investigations or findings.
LLM Security
Exploring the trust boundary between system instructions and untrusted retrieved content.
Agent Security
A proposed study of tool permissions, human approval, and the limits of agent autonomy.
Web Security
A sample methodology for tracing input, authorization, and evidence in isolated training labs.
07 / INTERACTIVE LAB
What happens when a document tries to become an instruction? Explore a controlled example.
SYSTEM POLICY
MODEL RESPONSE / SIMULATED
Ready to inspect a trust boundary.
Select a test case and run the simulation.
A deterministic teaching model, not an LLM or security detector. Preset patterns illustrate a concept; arbitrary inputs may not be recognized. No input leaves your browser.
An interactive, deterministic illustration of instruction priority. Runs entirely in your browser; no model or external target.
Open simulation ↗A proposed local harness for organizing adversarial test cases and documenting model behavior. Implementation has not started.
A planned notebook for reproducible lab walkthroughs, testing decisions, and mitigation notes. No findings published yet.
08 / CONTACT
For opportunities in cybersecurity, research collaboration, or a conversation about the work, reach me through my professional profile.