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.
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.
What you will be able to do
Understand the trust challenges of AI in defence.
Distinguish between interpretability and explainability approaches.
Apply explainability techniques to machine learning models.
Document models according to transparency criteria.
Evaluate model robustness, bias and uncertainty.
Design human-machine interactions with meaningful control.
Apply governance and ethics frameworks to defence AI.
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.
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
8 modules
1.1AI applications in defence1.2Decision support systems1.3Predictive maintenance and logistics1.4Image analysis1.5Calibrated trust in automation1.6Opacity of black-box models1.7NATO principles of responsible AI1.8Spanish Ministry of Defence AI strategy1.9Risks of AI in critical contexts1.10Case study: analysis of a logistics support system
2.1Interpretability versus explainability2.2Intrinsically interpretable models2.3Local and global explanations2.4Post hoc explanations2.5Audiences for explanations2.6Quality of explanations2.7DARPA XAI programme2.8Taxonomies of methods2.9Limitations of explanations2.10Workshop: decision tree versus neural network
3.1LIME3.2SHAP values3.3Saliency maps and Grad-CAM3.4Integrated gradients3.5Counterfactual explanations3.6Concept activation vectors3.7Prototype-based explanations3.8Explainability in language models3.9Fidelity evaluation3.10Lab: SHAP on an image classifier
4.1Model cards4.2Datasheets for datasets4.3Life-cycle traceability4.4Decision logging4.5Model version management4.6Algorithmic auditing4.7Transparency towards operators4.8Transparency towards supervisors4.9Limits imposed by security classification4.10Practical exercise: writing a model card
5.1Bias in training data5.2Fairness metrics5.3Uncertainty quantification5.4Out-of-distribution detection5.5Adversarial examples5.6Certified robustness5.7Data drift in service5.8Model monitoring5.9Stress testing5.10Lab: uncertainty quantification with ensembles
6.1Meaningful human control6.2Automation bias6.3Design of explanatory interfaces6.4Operator cognitive load6.5User evaluation6.6Operator training6.7Shared responsibility6.8Decisions under time pressure6.9Human-AI teams6.10Practical exercise: evaluation of an explanatory interface
7.1The EU AI Act and the defence exclusion7.2ISO/IEC 42001 AI management7.3ISO/IEC 23894 AI risk7.4DoD Directive 3000.097.5Legal review of new capabilities7.6UN debates on autonomy7.7Ethics committees7.8Algorithmic impact assessment7.9Accountability7.10Case study: impact assessment of a system
8.1Use case selection8.2Analysis of explainability requirements8.3Model selection8.4Application of XAI techniques8.5Documentation and transparency8.6User evaluation8.7Ethical and regulatory analysis8.8Conclusions8.9Report and presentation8.10Final project: final review with the tutor
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.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
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.
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.
Related programmes
Diploma in Nuclear Safety Organisational Culture
Online postgraduate diploma of 800 hours in nuclear safety organisational culture, structured in 8 modules covering the safety culture concept, leadership and management, human and organisational…
Diploma in SysML and MBSE in Military Programmes
Online postgraduate diploma of 800 hours in SysML and MBSE in military programmes. 8 modules covering MBSE in defence programmes, the SysML language, MBSE methodologies, requirements…
Diploma in EMC/EMI Standards MIL-STD-461/464
600-hour online postgraduate diploma in military electromagnetic compatibility: MIL-STD-461G and 464C, emissions and susceptibility, lightning, EMP, design for EMC and test programme management, with an assigned…
More in Defense, Military Engineering & Land Systems
All Defense, Military Engineering & Land Systems programmes → · How to apply · Fees & financing · Scholarships