DecipherU · Course 5
AI Security Engineering
For the cybersecurity engineer watching adversarial AI rewrite the threat surface every quarter. This 16-module course is for the practitioners who keep production AI safe, not the ones who watch it from the sidelines. Built on MITRE ATLAS, OWASP LLM Top 10, NIST AI 100-2, and the adversarial ML research canon (Goodfellow, Madry, Carlini, Greshake). 65-80 hours of study plus a 30-50 hour AI red team capstone. Reviewed by Julian Calvo, Ed.D., M.S.
What completing this course actually does for your comp
BLS OES May 2024 + Lightcast 2024 AI premiumTarget role after completion
AI Security Engineer
Base comp band: $138K–$167K (BLS median ± Enterprise tier).
With AI fluency (this course)
$174K–$189K
+20% to +30% lift on AI-fluent postings (Lightcast 2024).
Time investment
~75 hours
Self-paced. Most learners ship the capstone within 8–12 weeks of focused study.
What this replaces
Pricing posture
Standalone: $597. Bundled inside Operator ($129/mo) and Frontier ($299/mo), pays for itself if you would buy 3+ standalone courses.
Course author
Julian Calvo, Ed.D., M.S.
Founder of DecipherU. Combined background in education research, software engineering, and applied AI infrastructure, focused on the cybersecurity-AI convergence segment. Reviews every capstone with a security co-reviewer who has frontier-lab background where available.
After the course you can design, attack, and defend production AI systems with the rigor expected at frontier labs and AI-first companies.
Threat-model an LLM application end to end
Apply STRIDE adapted for AI, map threats to MITRE ATLAS tactics and techniques, and cross-reference the OWASP LLM Top 10. Produce a threat model an engineering team can act on.
Detect and mitigate every prompt injection variant
Direct injection, indirect injection, multi-modal injection, and multi-step agent injection. Build detection pipelines and mitigation layers referenced in OWASP LLM01 and the Greshake et al. indirect injection canon.
Implement adversarial-example attacks and defenses
Code FGSM, PGD, and C&W attacks against production classifiers following Goodfellow et al. and Madry et al. Implement adversarial training and certified robustness defenses with measured robustness guarantees.
Build production AI security infrastructure
Design and deploy the full stack: input validation gateway, output classifier (Llama Guard, ShieldGemma), NeMo Guardrails integration, audit log, and kill switch. Infrastructure that survives a security review.
Run an AI red team campaign with severity ratings
Scope, plan, execute, and report a full AI red team engagement. CVSS-style severity rating adapted for AI failure modes. Reproducer prompts, evidence, and prioritized remediation recommendations.
Defend against AI-enabled attacks
Detect and counter deepfake business email compromise, AI-assisted spear phishing, polymorphic AI-generated malware, and AI-driven reconnaissance. Build detection heuristics that work at enterprise scale.
Operationalize the production AI security observability stack
SLAs for AI security monitoring, incident response at frontier-lab scale, vendor security assessment for AI vendors, and model drift detection as a security signal.
Pass a frontier-lab AI security engineering interview loop
Threat modeling exercises, ML fundamentals questions (adversarial robustness, model extraction, training data attacks), system design for AI security, and behavioral dimensions. Practiced with the AI interview simulator in Module 15.
Sixteen modules cover the full discipline: AI security engineering fundamentals, threat modeling, prompt injection, jailbreaks, adversarial examples, training data attacks, model extraction, AI security infrastructure, agent security, AI red teaming, safety mechanisms, defending AI-enabled attacks, regulated industry AI security, production AI security at scale, and frontier lab interview preparation. Module 16 is a complete AI red team engagement capstone evaluated against the published rubric and a security co-reviewer.
The course maps every concept to its source so practitioners know where a technique comes from, not just what it is. Eight frameworks and research threads, made explicit.
Your organization just shipped an LLM-backed product and security owns the review. Your existing AppSec skills apply to maybe 40% of the threat surface. This course covers the other 60%: prompt injection, model behavior under adversarial input, output validation, and the guardrail infrastructure your team needs to build.
You know how to find vulnerabilities in traditional systems. AI red teaming adds prompt injection chains, jailbreak development, adversarial example construction, and model extraction to your toolkit. Module 10 builds the complete AI red team methodology. The capstone is a full engagement you can show in interviews.
Frontier labs hire security engineers who understand both ML systems and adversarial ML research. Module 15 covers exactly what those interview loops test. The capstone produces a red team engagement you can discuss at depth. The methodology synthesis gives you the vocabulary to engage with the research these teams publish.
This is a graduate-level technical course. The prerequisites are not suggestions.
Required
Recommended
Reviews
First cohort enrollment opens Q2 2026. Reviews from practitioners who complete the capstone will appear here once the first cohort finishes. Approved capstones in the top tier become anonymized case studies (with explicit permission).
Traditional AppSec assumes deterministic code. AI systems introduce probabilistic outputs, natural language attack surfaces, training data as an attack vector, and model behavior that shifts under adversarial input. Prompt injection has no direct analog in SAST/DAST tooling. Adversarial examples exploit the geometry of the model's learned representations. The threat model is fundamentally different, which changes what you build, test, and monitor.
The standard OWASP Top 10 covers web application vulnerability classes (injection, broken auth, IDOR, etc.). The OWASP Top 10 for LLM Applications covers AI-specific failure modes: prompt injection (LLM01), insecure output handling, training data poisoning, model denial of service, supply chain vulnerabilities, sensitive information disclosure, insecure plugin design, excessive agency, overreliance, and model theft. Many items have no equivalent in traditional web security.
Intermediate Python and security-engineering fundamentals are required. You do not need to have trained models from scratch. The course teaches the ML concepts that security engineers need: what a model's learned representation is, why adversarial examples exist geometrically, how fine-tuning changes model behavior, and how guardrail classifiers work. Familiarity with one ML library (PyTorch, TensorFlow, or Hugging Face) is recommended but not required on day one.
SEC547 is a solid foundation course covering AI security concepts in a SANS-style format. This course goes deeper into adversarial ML research (FGSM, PGD, C&W attacks with hands-on implementation), frontier lab practices (Anthropic Constitutional AI, RSP, OpenAI Preparedness Framework), and production AI security infrastructure (Llama Guard, ShieldGemma, NeMo Guardrails). The capstone is a full AI red team engagement, not a certification exam. The audiences overlap but the depth and the frontier-lab framing are different.
The credential signals that you completed a 65 to 80 hour course, passed technical knowledge checks at 80%, and delivered a reviewed AI red team engagement. That is evidence, not a shortcut. Frontier lab hiring teams at Anthropic, OpenAI, and Google DeepMind evaluate depth. Module 15 covers what those interviews actually test: threat modeling, ML fundamentals, system design for AI security, and behavioral. The credential will not substitute for that preparation, but it structures your study well.
Self-paced. Roughly 65 to 80 hours of structured study across 15 modules plus a 30 to 50 hour capstone deliverable. Most practitioners finish modules in 10 to 14 weeks at 5 to 7 hours per week, then evaluate the capstone against the published security rubric.
Every technical module includes a build exercise. Representative examples: implement FGSM and PGD attacks against a target classifier then implement adversarial training defenses; build a full input validation, output validation, and monitoring stack for an LLM-backed application; build a code-executing agent with sandboxing, capability boundaries, and a kill switch; run a prompt injection lab against direct, indirect, and multi-modal injection vectors. All exercises include tested code, ethical use rules, and grading rubrics.
Seven-day full refund from purchase, while you have completed less than 10% of the course. Email support@decipheru.com with your order number. After 7 days or above 10% completion, refunds are case-by-case. A refund triggers a 90-day lockout on re-purchasing this course or subscribing to a tier that bundles it. If the course is harder than expected but you want to complete it, the course community is there to bridge gaps.
The required prerequisites are intermediate Python and at least one applied security credential or equivalent experience (OSCP / OSED / GPEN / SAR or similar). If you are missing Python depth, a Python for security engineers module is planned as a free prerequisite. If you lack security fundamentals, the Cybersecurity Sales Mastery or SOC Analyst Fundamentals courses build general context, but applied security experience is genuinely required for this course to land.
The methodology citations (OWASP LLM Top 10, MITRE ATLAS, NIST AI 100-2) are versioned and updated when the source frameworks release new versions. Module content tied to specific model behaviors (guardrail classifiers, jailbreak variants, model extraction techniques) is reviewed every 90 days and flagged in the admin content health system when citations are older than 12 months. Enrolled practitioners get notified of material updates.
Each cert-prep add-on translates this practitioner course into a focused exam ramp for a named industry credential. The parent course teaches the discipline; the add-on bridges to the specific exam blueprint.
This course is part of a packaged path
Each path bundles the curriculum sequence, the compensation delta it unlocks, and the recommended courses (this one is on the list). If you are not sure which path matches your starting point, the 2-minute AI Risk Score routes you to the right one.
AI Security Operations Mastery
The SOC-track counterpart to this course. Covers AI-augmented detection, AI-powered threat intelligence, and AI SecOps tooling. Pair for end-to-end coverage.
$497 (bundled $797)
AI Engineering Mastery
The engineering foundation. RAG, fine-tuning, evaluation frameworks, agent architectures. Understanding what you are securing makes the security work sharper.
$597 (bundled $797)
AI Governance and Risk
The governance angle: NIST AI RMF, EU AI Act, model risk management, and the organizational structures that security engineers operate inside.
$497
Course content is for educational purposes only and does not constitute professional advice. All claims are supported by cited peer-reviewed academic research. DecipherU does not teach or reproduce any proprietary sales methodology. Verify all referenced sources independently.