Postgraduate DiplomaDefense, Military Engineering & Land Systems Applications open

Diploma in Explainability and Transparency in Defence AI

Online postgraduate diploma of 800 hours in explainability and transparency in defence AI. 8 modules covering trust in defence AI, explainability foundations and techniques, transparency and documentation, robustness and bias, human-machine interaction and AI governance, with an assigned technical tutor.

Duration6–8 months
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
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

Understand the trust challenges of AI in defence.

02

Distinguish between interpretability and explainability approaches.

03

Apply explainability techniques to machine learning models.

04

Document models according to transparency criteria.

05

Evaluate model robustness, bias and uncertainty.

06

Design human-machine interactions with meaningful control.

07

Apply governance and ethics frameworks to defence AI.

Profile

Who it's for

  • Trustworthy AI engineers.
  • Data scientists working in defence.
  • Algorithmic auditors.
  • Human factors specialists.
  • AI ethics advisers.
  • AI governance managers.
  • Engineering or science graduates seeking to enter the defence sector.
Standards & tools

What you'll work with

  • Regulation (EU) 2024/1689 (Artificial Intelligence Act)
  • ISO/IEC 42001:2023 (AI management systems)
  • ISO/IEC 23894:2023 (AI risk management)
  • DoD Directive 3000.09 (autonomy in weapon systems)
  • NATO Principles of Responsible Use of AI (2021) (responsible AI in defence)
  • ISO/IEC TR 24028 (trustworthiness in AI)
  • IEEE 7001-2021 (transparency of autonomous systems)
  • Python SHAP
  • Captum
  • LIME
  • PyTorch
  • IBM AI Explainability 360
Syllabus

8 modules

  1. 1.1AI applications in defence
  2. 1.2Decision support systems
  3. 1.3Predictive maintenance and logistics
  4. 1.4Image analysis
  5. 1.5Calibrated trust in automation
  6. 1.6Opacity of black-box models
  7. 1.7NATO principles of responsible AI
  8. 1.8Spanish Ministry of Defence AI strategy
  9. 1.9Risks of AI in critical contexts
  10. 1.10Case study: analysis of a logistics support system
  1. 2.1Interpretability versus explainability
  2. 2.2Intrinsically interpretable models
  3. 2.3Local and global explanations
  4. 2.4Post hoc explanations
  5. 2.5Audiences for explanations
  6. 2.6Quality of explanations
  7. 2.7DARPA XAI programme
  8. 2.8Taxonomies of methods
  9. 2.9Limitations of explanations
  10. 2.10Workshop: decision tree versus neural network
  1. 3.1LIME
  2. 3.2SHAP values
  3. 3.3Saliency maps and Grad-CAM
  4. 3.4Integrated gradients
  5. 3.5Counterfactual explanations
  6. 3.6Concept activation vectors
  7. 3.7Prototype-based explanations
  8. 3.8Explainability in language models
  9. 3.9Fidelity evaluation
  10. 3.10Lab: SHAP on an image classifier
  1. 4.1Model cards
  2. 4.2Datasheets for datasets
  3. 4.3Life-cycle traceability
  4. 4.4Decision logging
  5. 4.5Model version management
  6. 4.6Algorithmic auditing
  7. 4.7Transparency towards operators
  8. 4.8Transparency towards supervisors
  9. 4.9Limits imposed by security classification
  10. 4.10Practical exercise: writing a model card
  1. 5.1Bias in training data
  2. 5.2Fairness metrics
  3. 5.3Uncertainty quantification
  4. 5.4Out-of-distribution detection
  5. 5.5Adversarial examples
  6. 5.6Certified robustness
  7. 5.7Data drift in service
  8. 5.8Model monitoring
  9. 5.9Stress testing
  10. 5.10Lab: uncertainty quantification with ensembles
  1. 6.1Meaningful human control
  2. 6.2Automation bias
  3. 6.3Design of explanatory interfaces
  4. 6.4Operator cognitive load
  5. 6.5User evaluation
  6. 6.6Operator training
  7. 6.7Shared responsibility
  8. 6.8Decisions under time pressure
  9. 6.9Human-AI teams
  10. 6.10Practical exercise: evaluation of an explanatory interface
  1. 7.1The EU AI Act and the defence exclusion
  2. 7.2ISO/IEC 42001 AI management
  3. 7.3ISO/IEC 23894 AI risk
  4. 7.4DoD Directive 3000.09
  5. 7.5Legal review of new capabilities
  6. 7.6UN debates on autonomy
  7. 7.7Ethics committees
  8. 7.8Algorithmic impact assessment
  9. 7.9Accountability
  10. 7.10Case study: impact assessment of a system
  1. 8.1Use case selection
  2. 8.2Analysis of explainability requirements
  3. 8.3Model selection
  4. 8.4Application of XAI techniques
  5. 8.5Documentation and transparency
  6. 8.6User evaluation
  7. 8.7Ethical and regulatory analysis
  8. 8.8Conclusions
  9. 8.9Report and presentation
  10. 8.10Final project: final review with the tutor
Methodology, software & labs

How you'll learn

A 100% online programme on the SEIUM campus, with downloadable materials, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so the programme fits around your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python SHAP, Captum, LIME, PyTorch and IBM AI Explainability 360, in free, academic or evaluation versions. Tests are studied on real cases of applying explainability techniques to models, user evaluation of interfaces and model documentation with standardised cards. Assessment is continuous by module plus the final integrating project.

Standards covered: Regulation (EU) 2024/1689, ISO/IEC 42001:2023, ISO/IEC 23894:2023, DoD Directive 3000.09, NATO Principles of Responsible Use of AI (2021), ISO/IEC TR 24028, IEEE 7001-2021.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of Regulation (EU) 2024/1689, ISO/IEC 42001 and ISO/IEC 23894 applied to real cases, not as a theoretical annex.
Industry software:Python SHAP, Captum, LIME, PyTorch and IBM AI Explainability 360, in free, academic or evaluation versions.
Final project:an explainable AI project for a defence use case, from requirements to ethical and regulatory analysis, 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.

Select the use case
Choose a defence AI use case and analyse its explainability requirements.
Select the model
Select and train a model suited to the use case.
Apply XAI techniques
Apply and evaluate explainability techniques on the model.
Document and evaluate
Document the model transparently and evaluate it with users.
Final project
Present the project with its ethical and regulatory analysis, reviewed by your tutor.
Career opportunities

Where this takes you

Trustworthy AI engineerDefence data scientistAlgorithmic auditorHuman factors specialistAI ethics adviserAI governance manager
Admissions & scholarships

Requirements

  • Prior technical training or professional experience in the sector. A university degree is not required.
  • An internet connection and a computer capable of running the programme 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.

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 Python SHAP, Captum, LIME, PyTorch and IBM AI Explainability 360, 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 is required.

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

Diploma in Explainability and Transparency in Defence AIEnrol
Scroll to Top
SEIUM – Institute of Advanced Engineering
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.