Apply now
Postgraduate DiplomaData, AI, Simulation & Analytics Applications open

Diploma in Differential Privacy and Applied Crypto

Online postgraduate diploma of 800 hours in differential privacy and applied cryptography, with 8 modules covering re-identification risk, differential privacy, private machine learning, cryptographic foundations, homomorphic encryption, multiparty computation and PET system design, with an assigned technical tutor.

Duration6–8 months
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

Analyse re-identification risks and threat models.

02

Apply differential privacy mechanisms while controlling the privacy budget.

03

Train machine learning models with differential privacy guarantees.

04

Use modern cryptographic primitives securely.

05

Implement computations on encrypted data with homomorphic schemes.

06

Design solutions with multiparty computation and other PETs.

07

Document privacy guarantees in line with the regulatory framework.

Profile

Who it's for

  • Privacy engineers looking to deepen their command of differential privacy and applied cryptography.
  • Applied cryptographers who want to add formal privacy guarantees to their toolkit.
  • Data scientists working with sensitive data in health, banking or the public sector.
  • Security architects designing systems that process personal data.
  • Data protection consultants who need a solid technical grounding in PETs.
  • Researchers in privacy-enhancing technologies.
  • Engineering or science graduates aiming to enter the health sector.
Standards & tools

What you'll work with

  • ISO/IEC 20889:2018 (privacy-enhancing de-identification techniques)
  • NIST SP 800-226 (guidelines for evaluating differential privacy guarantees)
  • Regulation (EU) 2016/679 – GDPR (EU data protection regulation)
  • ISO/IEC 27559:2022 (de-identification framework)
  • ISO/IEC 18033-6:2019 (homomorphic encryption)
  • FIPS 197 (AES encryption standard)
  • FIPS 203 (ML-KEM post-quantum key encapsulation)
  • FIPS 204 (ML-DSA post-quantum digital signatures)
  • OpenDP
  • Opacus
  • OpenFHE
  • Microsoft SEAL
  • MP-SPDZ
Syllabus

8 modules

  1. 1.1Privacy threat models
  2. 1.2Linkage and re-identification attacks
  3. 1.3k-anonymity, l-diversity and t-closeness
  4. 1.4Database reconstruction attacks
  5. 1.5Membership inference in models
  6. 1.6De-identification techniques in ISO/IEC 20889
  7. 1.7The ISO/IEC 27559 framework
  8. 1.8Anonymisation under the GDPR
  9. 1.9Historical re-identification cases
  10. 1.10Workshop: linkage attack on a public dataset
  1. 2.1Definition of epsilon-differential privacy
  2. 2.2Global and local sensitivity
  3. 2.3Laplace and Gaussian mechanisms
  4. 2.4Exponential mechanism for selection
  5. 2.5Composition and privacy budget
  6. 2.6Rényi differential privacy and zCDP
  7. 2.7Local differential privacy
  8. 2.8Post-processing and invariance
  9. 2.9Choosing epsilon in practice
  10. 2.10Lab: queries with OpenDP
  1. 3.1DP-SGD and gradient clipping
  2. 3.2Privacy accounting with the moments accountant
  3. 3.3Opacus and TensorFlow Privacy
  4. 3.4Differential privacy in federated learning
  5. 3.5Differentially private synthetic data
  6. 3.6Official statistics with differential privacy
  7. 3.7Privacy–utility trade-off
  8. 3.8Empirical auditing of guarantees
  9. 3.9The NIST SP 800-226 guideline
  10. 3.10Lab: training with DP-SGD in Opacus
  1. 4.1AES symmetric encryption
  2. 4.2RSA and elliptic-curve public-key cryptography
  3. 4.3Hash functions and digital signatures
  4. 4.4Key exchange protocols
  5. 4.5Post-quantum cryptography: ML-KEM and ML-DSA
  6. 4.6Key management
  7. 4.7Random number generation
  8. 4.8Side-channel attacks
  9. 4.9Secure cryptographic libraries
  10. 4.10Practical: authenticated encryption with libsodium
  1. 5.1Partially homomorphic schemes
  2. 5.2Paillier and its applications
  3. 5.3BFV and BGV schemes
  4. 5.4CKKS scheme for approximate numbers
  5. 5.5Bootstrapping and multiplicative depth
  6. 5.6Parameters and security level
  7. 5.7Inference on encrypted data
  8. 5.8Performance and limitations
  9. 5.9Standardisation in ISO/IEC 18033-6
  10. 5.10Lab: regression on encrypted data with OpenFHE
  1. 6.1Shamir secret sharing
  2. 6.2SPDZ protocols and garbled circuits
  3. 6.3Private set intersection
  4. 6.4Secure aggregation protocols
  5. 6.5Zero-knowledge proofs
  6. 6.6Trusted execution environments
  7. 6.7Functional encryption and its uses
  8. 6.8Comparison of privacy-enhancing technologies
  9. 6.9PET guidance from data protection authorities
  10. 6.10Practical: three-party secure sum with MP-SPDZ
  1. 7.1Choosing the technology for each case
  2. 7.2Combined PET architectures
  3. 7.3Residual risk assessment
  4. 7.4Performance and cost in production
  5. 7.5GDPR compliance with PETs
  6. 7.6Impact assessments
  7. 7.7Technical documentation of privacy guarantees
  8. 7.8Common implementation errors
  9. 7.9Third-party validation
  10. 7.10Case study: health statistics shared between hospitals
  1. 8.1Case definition and threats
  2. 8.2Privacy requirements analysis
  3. 8.3Selection of techniques
  4. 8.4Implementation of differential privacy
  5. 8.5Implementation of the cryptographic component
  6. 8.6Utility and performance evaluation
  7. 8.7Residual risk analysis
  8. 8.8Documentation of guarantees
  9. 8.9Report and presentation
  10. 8.10Final project: final review with the tutor
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 each intake, so it can be combined with work.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is OpenDP, Opacus, OpenFHE, Microsoft SEAL and MP-SPDZ, in free, academic or evaluation versions. Real procedures are studied: re-identification attacks on published data, training models with differential privacy, computation on encrypted data and multiparty protocols. Assessment is continuous by module plus the final integrative project.

Standards covered: ISO/IEC 20889:2018, NIST SP 800-226, Regulation (EU) 2016/679 (GDPR), ISO/IEC 27559:2022, ISO/IEC 18033-6:2019, FIPS 197 (AES), FIPS 203 (ML-KEM), FIPS 204 (ML-DSA).

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ISO/IEC 20889, NIST SP 800-226 and the GDPR applied to real cases, not as a theoretical annex.
Industry software:OpenDP, Opacus, OpenFHE, Microsoft SEAL and MP-SPDZ, in free, academic or evaluation versions.
Final project:a documented privacy and cryptography project combining differential privacy with a cryptographic component on a real case, reviewed by your tutor.
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.

Threat modelling
Define the case, its threats and the privacy requirements to be met.
Technique selection
Choose the differential privacy and cryptographic techniques that fit the case.
Differential privacy implementation
Implement the differentially private analysis with a controlled privacy budget.
Cryptographic component
Build the encrypted or multiparty component and evaluate utility and performance.
Final project
Document the guarantees and residual risk, and present the report for review by your tutor.
Career opportunities

Where this takes you

Privacy engineerApplied cryptographerPrivacy-focused data scientistSecurity architectData protection consultantPrivacy-enhancing technologies researcher
Admissions & scholarships

Requirements

  • Prior technical training or professional experience in the sector. No university degree is required.
  • 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 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with OpenDP, Opacus, OpenFHE, Microsoft SEAL and MP-SPDZ, 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 final project. 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 are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.

Prior technical training or professional experience in the sector (no university degree required), a computer able to run the 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
Postgraduate Diploma2,000 $

Diploma in Time Series Models for Engineering (ARIMA→DL)

Online postgraduate diploma of 800 hours in time series models for engineering, from ARIMA to deep learning. 8 modules covering ARIMA and state-space models, machine learning…

800 hours · 6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma1,440 $

Diploma in Security Policies and Stability in RL

Online postgraduate diploma of 800 hours in policy safety and stability in RL: 8 modules covering risks in reinforcement learning, constrained RL, shields and safety filters,…

6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma1,670 $

Diploma in Applied Causal Inference (DAGs, IV, DID)

Online postgraduate diploma of 800 hours in applied causal inference (DAGs, IV, DID). 8 modules covering potential outcomes, directed acyclic graphs, confounder adjustment and double machine…

6–8 monthsOnlineData, AI, Simulation & Analytics
Diploma in Differential Privacy and Applied CryptoEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Diploma in Classical and Deep RL for Dynamic SystemsView programme →Diploma in Real-Time Operational AnalyticsView programme →Diploma in Geo-Temporal Predictive ModelsView programme →Diploma in Value Metrics and Data MonetizationView programme →Diploma in PdM Deployment: Integration with SCADA/CMMSView programme →Diploma in Stateful and Exactly-Once Pipeline DesignView 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.