Wirewalk Instituteof AI
sec-320 Expert Waitlist

Securing the AI Supply Chain

For security architects, MLOps and platform engineers who must verify where models, datasets, libraries and agent tools came from and stop tampered artifacts reaching production.

The curriculum is being prepared and reviewed. Enrollment is not open yet.

About this course

Few organizations train their own foundation models. They download weights from model hubs, fine-tune with open datasets, install fast-moving ML libraries, pull inference containers and connect agent tools and MCP servers written by others. Every one of those links can be tampered with, and some, such as pickle-based model files, can execute code the moment they are loaded. This course teaches you to secure that chain with the same rigor mature teams apply to software, using frameworks current as of October 2026: SLSA v1.2 (build and source tracks), NIST SP 800-218 and its generative AI profile SP 800-218A, the OpenSSF Model Signing (OMS) specification with Sigstore, CycloneDX ML-BOM and the SPDX 3.0 AI and Dataset profiles.

You will learn why safetensors and similar formats reduce risk, what model scanners can and cannot detect, and why backdoored weights are hard to find by inspection. You will sign and verify model artifacts, capture provenance for training and fine-tuning pipelines, enforce verification at deployment with admission policies, and maintain AI BOMs, model cards and license records through retraining. The course covers ML framework and inference server vulnerabilities, third-party model APIs, and agent tools and MCP servers as supply chain, then closes with a model registry and promotion gates, incident response for a compromised artifact, and a maturity roadmap. The Wirewalk Institute certificate attests to completion and assessment of this course; it is not endorsed by OWASP, MITRE, NIST or any vendor named here.

What you will be able to do

  • Map the AI supply chain for a system and identify the threats to each component
  • Explain the code-execution risk of unsafe serialization formats and choose safer formats and loading practices
  • Sign and verify model artifacts using the OpenSSF Model Signing specification and Sigstore
  • Produce build provenance for training and fine-tuning pipelines aligned to SLSA
  • Create and maintain AI bills of materials using CycloneDX ML-BOM or SPDX 3.0 profiles
  • Assess third-party model APIs, agent tools and MCP servers as supply chain dependencies
  • Design a model registry with promotion gates and an incident response plan for a compromised artifact

Syllabus

6 modules · 18 lessons · about 18 hours

Module 1: Mapping the AI Supply Chain

Components, threats and the frameworks that apply.
3 lessons
  1. Components: Base Models, Adapters, Datasets, Libraries, Containers and Tools
  2. Threats to Each Link: Backdoors, Malicious Serialization, Typosquatting and Compromised Hubs
  3. Frameworks: SLSA v1.2, NIST SP 800-218A and the OWASP Supply Chain Entries

Module 2: Model Artifacts and Serialization

Loading models safely and the limits of inspection.
3 lessons
  1. Pickle, Code Execution and Safer Formats Such as safetensors
  2. Scanning Model Files: What Scanners Detect and What They Miss
  3. Backdoored and Trojaned Models: Why Inspection Falls Short

Module 3: Provenance, Signing and Attestation

Proving where an artifact came from and enforcing it.
3 lessons
  1. Model Signing with the OpenSSF Model Signing Specification and Sigstore
  2. Build Provenance for Training and Fine-Tuning Pipelines
  3. Verifying at Deployment: Admission Policies and Trusted Registries

Module 4: Bills of Materials and Documentation

Recording what a model is made of and the obligations that come with it.
3 lessons
  1. AI BOMs with CycloneDX ML-BOM and SPDX 3.0 AI and Dataset Profiles
  2. Model Cards, Dataset Cards and License Obligations
  3. Keeping BOMs Accurate Across Retraining and Updates

Module 5: Dependencies and Third-Party Services

Libraries, servers, APIs and tools you did not build.
3 lessons
  1. ML Framework and Inference Server Vulnerabilities
  2. Third-Party Model APIs: Assessment and Contract Controls
  3. Agent Tools, Plugins and MCP Servers as Supply Chain

Module 6: Building the Program

Registries, response and a roadmap.
3 lessons
  1. An Internal Model Registry with Promotion Gates
  2. Responding to a Compromised Model or Dataset
  3. An AI Supply Chain Maturity Roadmap

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 25 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 60 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by OpenSSF, Sigstore, SLSA, CycloneDX, SPDX, Hugging Face, or NIST. Product and company names are trademarks of their respective owners.

More in AI Security: Securing AI Systems

All 13 courses in this track
sec-001 Free intro Available

Using AI Safely at Work: The Essentials

Follow one fictional US distributor through four everyday AI mistakes (a guarantor's credit file uploaded to a personal account, a customer letter promising a fee waiver that does not exist, a vendor email with hidden instructions for the assistant, and a note-taker that sent a customer the internal margin floor) and practice the decisions that prevent or contain each one in three short Decision Labs.

1 h · 7 lessons Free intro
sec-101 Basic Available

Using AI Safely: Data Handling for Every Employee

A plain-language course on handling data safely with AI tools: what happens to what you type or upload, how to classify before you paste, how connected apps and agents change the picture, and how to report a mistake quickly.

6 h · 15 lessons See price at checkout
sec-201 Intermediate Available

AI Security Fundamentals: The OWASP Top 10 for LLMs

A practitioner course on securing applications that use large language models, organized around the 2026 OWASP Top 10 for LLM Applications. Every risk comes with a hypothetical scenario, the root cause, and concrete defenses in code and configuration.

14 h · 18 lessons See price at checkout