Learning Paths

Build a working mental model of private AI, select suitable models, and launch a practical local assistant.

Turn available hardware into a secure, usable local inference workstation across common desktop platforms.

Install, tune, expose, monitor, and maintain local model services with multiple serving options.

Build private assistants, retrieval systems, agents, and operational dashboards on controlled model infrastructure.

Design, scale, observe, and control AI workloads distributed across local servers and rented cloud capacity.

Identify, model, test, and govern security risks across models, agents, supply chains, and AI-enabled applications.

Select, run, and expose local vision-capable models while keeping image workflows under operator control.

Use conversational coding, prompt design, controlled loops, and security validation to turn model output into maintainable software.

Move from telemetry and adversary models into detection development, exposure prioritization, and proactive hunting.

Establish an incident-response workflow and investigate evidence across desktop, mobile, browser, removable-media, and malware sources.

Operate cloud defenses across identity, containers, exposure management, resilience, and incident response.

Develop a disciplined public-information investigation workflow from digital-footprint concepts through technical collection and verification.

Develop analytic discipline for threat research, adversary profiling, deception resistance, and cross-jurisdiction coordination.

Prioritize exposure, apply intelligence, manage container remediation, and sustain evidence-driven vulnerability operations.

Reduce attack surface across Linux hosts, networks, credentials, files, administrative interfaces, and volatile environments.

Build a broad application-security foundation spanning design, identity, data handling, secrets, and security testing.

Progress from industrial architecture and protocols through monitoring, hunting, resilience, vulnerability management, and standards.

Build Python applications that validate data, protect model interactions, and constrain agent behavior.

Understand C memory hazards, then apply safer input, API, bounds, allocation, and cryptographic practices.

Secure TypeScript and Node.js applications from runtime input boundaries through identity, secrets, storage, and testing.

Write safer administrative automation that handles commands, files, credentials, secrets, and host state defensively.

Secure containerized workloads through architecture, vulnerability management, patching, escape threat modeling, secrets, and testing.

Plan and perform layered application assessment using design review, validation analysis, static testing, dynamic testing, and AI assistance.

Move from framework orientation into detailed control, assurance, and continuous-monitoring requirements across major security programs.

Understand the quantum risk, current NIST standards, and practical migration implications for long-lived data and web services.

Understand FedRAMP scope, baselines, High requirements, NIST control foundations, evidence, vulnerability management, and continuous monitoring.

Apply neuroplasticity, cognitive load, sleep, motivation, metacognition, and reflection to improve durable learning.

Build a repeatable performance-improvement system using deliberate practice, motivation, feedback, reflection, time, and energy.

Improve judgment under uncertainty through critical thinking, probabilistic reasoning, structured analysis, metacognition, and reflection.

Design instruction with learning science and ADDIE, then produce polished course assets with common authoring and creative tools.

Plan and support drone missions across environmental, night, observation, inspection, thermal, navigation-threat, and operations-center concerns.