Wirewalk Instituteof AI
sec-330 Expert Waitlist

Privacy-Preserving AI

For ML engineers, privacy engineers and security architects who must train and deploy models on sensitive data while limiting what those models can reveal.

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

About this course

A model trained on sensitive data can leak it: attackers can infer whether a record was in the training set, reconstruct attributes, or extract memorized text from a generative model. NIST AI 100-2 E2025 classes these as privacy attacks alongside evasion, poisoning and misuse. This course teaches the techniques that reduce that leakage and, just as important, how to tell what guarantee each one really provides.

You will learn differential privacy from first principles (epsilon, delta, composition), train and fine-tune with DP-SGD using Opacus, choose and evaluate privacy budgets with NIST SP 800-226 (final, March 2025), and generate differentially private synthetic data. You will examine federated learning with frameworks such as Flower, what secure aggregation does and does not protect, and attacks on federated updates. The cryptographic and hardware module compares homomorphic encryption, secure multi-party computation and confidential computing on CPUs and GPUs by cost, latency and trust assumptions. For LLM systems you will design de-identification before training and retrieval, privacy-preserving inference gateways, and assess machine unlearning. The course closes with LINDDUN privacy threat modeling, mapping techniques to GDPR and EU AI Act data governance duties, and auditing models with attack simulations. The course is educational and is not legal advice. Operational data security for RAG stores and logs is covered in sec-230. 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

  • Explain membership inference, attribute inference, model inversion and training data extraction and how to measure each
  • Apply differential privacy correctly, including composition and budget accounting, and train with DP-SGD
  • Evaluate a differential privacy claim using NIST SP 800-226
  • Compare federated learning, secure aggregation, homomorphic encryption, secure computation and confidential computing by guarantee, cost and trust assumptions
  • Design de-identification and privacy-preserving inference for LLM applications
  • Model privacy threats with LINDDUN and audit a model's privacy with attack simulations

Syllabus

6 modules · 19 lessons · about 18 hours

Module 1: Privacy Attacks on Machine Learning

What models leak and how attackers extract it.
3 lessons
  1. Membership Inference, Attribute Inference and Model Inversion
  2. Training Data Extraction from Generative Models
  3. Privacy Attacks in the NIST AI 100-2 Taxonomy

Module 2: Differential Privacy

The definition, the training algorithm and how to judge a claim.
4 lessons
  1. Epsilon, Delta and Composition: Differential Privacy Without Hand-Waving
  2. DP-SGD for Training and Fine-Tuning with Opacus
  3. Choosing and Evaluating Privacy Budgets with NIST SP 800-226
  4. Differentially Private Synthetic Data

Module 3: Federated and Decentralized Learning

Keeping data in place and what that does and does not protect.
3 lessons
  1. Federated Learning Architectures and Their Real Guarantees
  2. Secure Aggregation and Attacks on Federated Updates
  3. When Federated Learning Is the Wrong Tool

Module 4: Cryptographic and Hardware Approaches

Computing on data you cannot see.
3 lessons
  1. Homomorphic Encryption and Secure Multi-Party Computation for ML
  2. Confidential Computing for AI: CPU TEEs, GPU Confidential Computing and Attestation
  3. Trade-offs: Cost, Latency and Trust Assumptions

Module 5: Privacy in LLM Applications

Practical privacy for training, retrieval and inference with language models.
3 lessons
  1. De-identification and Pseudonymization Before Training and Retrieval
  2. Privacy-Preserving Inference Gateways and Retrieval
  3. Machine Unlearning: Methods and Limits

Module 6: Privacy Engineering in Practice

Threat modeling, regulatory mapping and auditing.
3 lessons
  1. Privacy Threat Modeling with LINDDUN
  2. Mapping Techniques to GDPR and EU AI Act Data Governance Duties
  3. Auditing Model Privacy with Attack Simulations

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 NIST, OpenDP, Meta Opacus, Flower, or NVIDIA. 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