Apply now
Master'sData, AI, Simulation & Analytics Applications open

Master’s in Federated Learning & Privacy-Preserving ML Engineering

Online master's programme of 1,900 hours in federated learning and privacy-preserving machine learning engineering. 12 modules covering ML privacy threats, federated learning foundations, heterogeneity, communication and scalability, vertical and cross-organisation federation, differential privacy, secure aggregation, attacks and defences, foundation models, federated MLOps and regulation, with an assigned technical tutor.

Duration1900 h
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

Take the controls.

Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Design cross-device and cross-silo federated learning systems.

02

Address data and system heterogeneity in federated settings.

03

Apply differential privacy to model training.

04

Implement secure aggregation and cryptographic techniques.

05

Evaluate attacks and defences in federated learning.

06

Deploy federated solutions in production.

07

Analyse the regulatory fit of PPML projects.

Profile

Who it's for

  • Federated learning engineers scaling training across devices and silos.
  • ML privacy engineers applying differential privacy and secure aggregation.
  • PPML researchers working on attacks, defences and auditing.
  • Secure AI systems architects designing production federated platforms.
  • Healthcare data scientists collaborating across hospitals without sharing data.
  • Privacy technology consultants advising on PETs and regulation.
  • Engineering or science graduates aiming to enter the healthcare sector.
Standards & tools

What you'll work with

  • Regulation (EU) 2016/679 (GDPR)
  • ISO/IEC 27701 (privacy information management)
  • Regulation (EU) 2022/868 (Data Governance Act)
  • ISO/IEC 29100 (privacy framework)
  • ISO/IEC 20889 (privacy-enhancing data de-identification techniques)
  • Regulation (EU) 2024/1689 (AI Act)
  • IEEE 3652.1 (architectural framework for federated machine learning)
  • Flower
  • NVIDIA FLARE
  • Opacus
  • OpenFHE
  • TensorFlow Federated
Syllabus

12 modules · 1900 h

  1. 1.1The ML life cycle and exposure points
  2. 1.2Personal data in training and inference
  3. 1.3Threat models
  4. 1.4Honest-but-curious and malicious attackers
  5. 1.5Privacy-enhancing technologies
  6. 1.6Trade-offs between privacy, utility and cost
  7. 1.7Use cases that motivate federated learning
  8. 1.8State of the art in PPML
  9. 1.9Regulatory privacy requirements
  10. 1.10Case study: threats in a medical diagnosis system
  1. 2.1Formulation of federated optimisation
  2. 2.2FedAvg and FedSGD
  3. 2.3Cross-device versus cross-silo federated learning
  4. 2.4Horizontal, vertical and transfer federated learning
  5. 2.5Client selection and sampling
  6. 2.6Rounds, local epochs and convergence
  7. 2.7Federated evaluation metrics
  8. 2.8Simulation of federated scenarios
  9. 2.9Framework ecosystem
  10. 2.10Lab: first federated training with Flower
  1. 3.1Non-IID data and its types
  2. 3.2FedProx and proximal regularisation
  3. 3.3SCAFFOLD and drift correction
  4. 3.4Normalisation in federated settings
  5. 3.5System heterogeneity
  6. 3.6Per-client federated personalisation
  7. 3.7Federated learning with client clustering
  8. 3.8Fairness across clients
  9. 3.9LEAF and FLamby benchmarks
  10. 3.10Practical exercise: comparison of FedAvg, FedProx and SCAFFOLD
  1. 4.1Communication cost
  2. 4.2Compression and quantisation of updates
  3. 4.3Gradient sparsification
  4. 4.4Asynchronous federated learning
  5. 4.5Hierarchical and decentralised topologies
  6. 4.6Peer-to-peer learning
  7. 4.7Federated learning at the edge and on mobile devices
  8. 4.8Dropout tolerance
  9. 4.9Large-scale deployments
  10. 4.10Workshop: update compression in Flower
  1. 5.1Feature partitioning
  2. 5.2Private entity alignment
  3. 5.3Split models and split learning
  4. 5.4Federated decision trees
  5. 5.5Vertical federated learning with encryption
  6. 5.6Consortia and governance
  7. 5.7Incentives and contribution valuation
  8. 5.8Federated learning in banking and insurance
  9. 5.9Federated learning in healthcare across hospitals
  10. 5.10Lab: vertical federated logistic regression
  1. 6.1Definition and properties
  2. 6.2Additive noise mechanisms
  3. 6.3Rényi privacy accounting
  4. 6.4DP-SGD and gradient clipping
  5. 6.5User-level differential privacy
  6. 6.6Differential privacy in federated learning
  7. 6.7Private hyperparameter tuning
  8. 6.8Impact on accuracy and fairness
  9. 6.9Using the Opacus library
  10. 6.10Practical exercise: DP-SGD training in Opacus
  1. 7.1Secure aggregation protocols
  2. 7.2Shamir's secret sharing
  3. 7.3Homomorphic encryption in aggregation
  4. 7.4Multi-party computation for training
  5. 7.5Trusted execution environments
  6. 7.6Private inference as a service
  7. 7.7Cost and latency
  8. 7.8OpenFHE and CrypTen libraries
  9. 7.9Design of hybrid protocols
  10. 7.10Lab: secure aggregation with secret sharing
  1. 8.1Gradient-based data reconstruction
  2. 8.2Membership inference
  3. 8.3Property inference
  4. 8.4Data and model poisoning
  5. 8.5Backdoor attacks
  6. 8.6Robust aggregation: Krum and median
  7. 8.7Detection of malicious clients
  8. 8.8Privacy auditing
  9. 8.9Evaluation of defences
  10. 8.10Workshop: gradient reconstruction attack and defence
  1. 9.1Federated fine-tuning of large models
  2. 9.2LoRA and adapters in federated learning
  3. 9.3Federated language models
  4. 9.4Privacy in LLM fine-tuning
  5. 9.5Memorisation and extraction
  6. 9.6Synthetic data as an alternative
  7. 9.7Machine unlearning in federated learning
  8. 9.8Cost on devices
  9. 9.9Research trends
  10. 9.10Practical exercise: federated fine-tuning with LoRA
  1. 10.1Production architecture
  2. 10.2Client orchestration
  3. 10.3Model version management
  4. 10.4Monitoring without data access
  5. 10.5Federated evaluation in production
  6. 10.6Infrastructure security
  7. 10.7Deployment with NVIDIA FLARE
  8. 10.8Certificates and identities
  9. 10.9Auditing and traceability
  10. 10.10Lab: cross-silo federated deployment with NVIDIA FLARE
  1. 11.1GDPR and federated learning
  2. 11.2Legal bases and responsibilities
  3. 11.3Data protection impact assessment
  4. 11.4Anonymisation under the GDPR
  5. 11.5Data Governance Act
  6. 11.6European Health Data Space
  7. 11.7The AI Act and training data
  8. 11.8Consortium agreements
  9. 11.9ISO/IEC privacy standards
  10. 11.10Case study: governance agreement for a federated consortium
  1. 12.1Definition of the federated scenario
  2. 12.2Threat model
  3. 12.3Design of the training protocol
  4. 12.4Privacy and security mechanisms
  5. 12.5Implementation and simulation
  6. 12.6Evaluation of utility, privacy and cost
  7. 12.7Regulatory analysis of the scenario
  8. 12.8Conclusions and future work
  9. 12.9Master's Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within the intake, so you can combine it with your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is Flower, NVIDIA FLARE, Opacus, OpenFHE and TensorFlow Federated, in free, academic or evaluation versions. Practical work is based on real procedures: federated training across hospitals, learning with differential privacy and evaluation of gradient reconstruction attacks. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: Regulation (EU) 2016/679, ISO/IEC 27701, Regulation (EU) 2022/868, ISO/IEC 29100, ISO/IEC 20889, Regulation (EU) 2024/1689, IEEE 3652.1.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of the GDPR (Regulation (EU) 2016/679), ISO/IEC 27701 and the Data Governance Act (Regulation (EU) 2022/868) applied to real cases, not as a theoretical annex.
Industry software:Flower, NVIDIA FLARE, Opacus, OpenFHE and TensorFlow Federated, in free, academic or evaluation versions.
Master's Thesis with defence:A complete federated learning scenario with threat model, privacy and security mechanisms and an evaluation of utility, privacy and cost, defended before a panel.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Model the threats
Define the federated scenario and its threat model.
Train with heterogeneity
Compare FedAvg, FedProx and SCAFFOLD on non-IID data in Flower.
Add privacy and security
Apply DP-SGD with Opacus and secure aggregation with secret sharing.
Deploy across silos
Deploy and monitor a cross-silo federation with NVIDIA FLARE.
Master's Thesis
A federated system evaluated for utility, privacy, cost and regulatory fit, defended before a panel.
Career opportunities

Where this takes you

Federated learning engineerML privacy engineerPPML researcherSecure AI systems architectHealthcare data scientistPrivacy technology consultant
Admissions & scholarships

Requirements

  • A university degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • An internet connection and a computer capable of running the programme's software.
  • English sufficient to read technical standards.

Ready to start?

Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with Flower, NVIDIA FLARE, Opacus, OpenFHE and TensorFlow Federated, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.

A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.

Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.

A university degree in engineering, science or architecture (or equivalent professional experience), a computer able to run the programme's software and English sufficient to read technical standards.

Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.

Keep exploring

Related programmes

See all in Data, AI, Simulation & Analytics
Master's9,970 $

Master’s in Data Product Management for Engineering

Online master's programme of 1,900 hours in data product management for engineering. 12 modules covering the data product manager role, opportunity discovery, product strategy, requirements and…

1900 hOnlineData, AI, Simulation & Analytics
Master's7,730 $

Master’s in Time Series, Signals and Anomaly Detection Engineering

Online master's programme of 1,900 hours in time series, signals and anomaly detection: 12 modules covering the nature of anomalies, signal preprocessing, classical statistical methods, change…

1900 hOnlineData, AI, Simulation & Analytics
Master's8,850 $

Master’s in Multiphysics Co-Simulation & FMI Engineering

Online master's programme of 1,900 hours in multiphysics co-simulation and FMI engineering. 12 modules covering multiphysics systems, the FMI standard in depth, co-simulation algorithms, SSP system…

1900 hOnlineData, AI, Simulation & Analytics
Master’s in Federated Learning & Privacy-Preserving ML EngineeringEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Master’s in Synthetic Data and Sensor Simulation EngineeringView programme →Master’s in Causality and Experimentation EngineeringView programme →Master’s in Industrial Data & Platform MLOps EngineeringView programme →Master’s in Digital Twin Engineering for Energy and GridsView programme →Master’s in Simulation, Co-Simulation and HPC EngineeringView programme →Master’s in Reinforcement Learning, Control and Safe AI EngineeringView programme →

All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.