Diploma in Anomaly and Attack Detection in Graphs
Online postgraduate diploma of 800 hours in anomaly and attack detection on graphs, with 8 modules covering anomalous behaviour in graphs, classical and deep learning detection methods, dynamic and streaming graphs, graphs in cybersecurity, adversarial attacks on graph models and operation, governance and compliance, with an assigned technical tutor.
Diploma in Anomaly and Attack Detection in Graphs — studying from Singapore
Singapore has invested heavily in artificial intelligence and data, under national plans coordinated by the Infocomm Media Development Authority and the AI Singapore programme. The sector spans industrial analytics, digital twins, simulation for engineering design and data platforms serving finance, logistics and healthcare. Engineers work across machine learning, data engineering and computational modelling. Employers range from global technology firms and banks to local research institutes and government-linked companies.
Fees for Singapore: S$2,560 (Singapore dollar), with instalments and employer sponsorship available.
Relevant bodies in Singapore
Typical roles
Questions from Singapore
Does Singapore have a recognised body for data and AI professionals, and is SEIUM recognised?
Singapore's Infocomm Media Development Authority (IMDA) and the Singapore Computer Society are key bodies in the digital and data field, and the Personal Data Protection Commission (PDPC) oversees data protection. SEIUM's qualifications are private, not state degrees, and not accredited by any national body. Acceptance is decided by employers or the relevant body, so verify this before enrolling.
Which Singapore employers hire data, AI and simulation specialists?
Demand is strong across banks, government agencies, healthcare, logistics, telecoms and tech firms. Singapore's national AI and smart nation initiatives also create roles. Employers typically assess portfolios, technical interviews and proven projects. Your final project can demonstrate applied analytics or simulation skills, though hiring decisions are the employer's.
Can I study this part-time from Singapore, and does it need a student visa?
Yes, the programmes are 100% online and taught in English, so you can study from Singapore without a student visa. Workload is substantial, with 1,900 hours for a master's, 800 for a postgraduate diploma and 300 for a specialist course. Fees can be paid in instalments, and employer sponsorship is possible, subject to your employer's approval.
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
Characterise the types of anomaly in static, dynamic and heterogeneous graphs.
Apply classical methods such as OddBall and Fraudar to transaction graphs.
Train autoencoders and GNNs for anomaly detection with imbalanced classes.
Detect anomalies in real time on edge streams.
Analyse attack paths and lateral movement using security graphs.
Assess and mitigate adversarial attacks against graph models.
Integrate detection into investigation processes that comply with regulations.
Who it's for
- Anti-fraud data scientists in banking and payments.
- Cybersecurity analysts using graph-based techniques.
- SOC detection engineers.
- Anti-money laundering specialists.
- Adversarial machine learning researchers.
- Machine learning engineers working on risk models.
- Engineering or science graduates aiming to enter banking and payments.
What you'll work with
- ISO/IEC 27001:2022 (information security management systems)
- Regulation (EU) 2016/679 – GDPR (General Data Protection Regulation)
- Directive (EU) 2015/849 (prevention of money laundering)
- Directive (EU) 2022/2555 – NIS2 (network and information security)
- ISO/IEC 27035 (information security incident management)
- NIST SP 800-61 Rev. 2 (incident handling)
- ISO/IEC 42001:2023 (AI management systems)
- Regulation (EU) 2024/1689 (Artificial Intelligence Act)
- PyGOD
- PyTorch Geometric
- Neo4j Graph Data Science
- BloodHound
- DeepRobust
8 modules
1.1Types of anomaly: nodes, edges, subgraphs and graphs1.2Static, dynamic and heterogeneous graphs1.3Centrality measures and local structure1.4Egonets and neighbourhood patterns1.5Power laws and degree distributions1.6Transaction, network and identity graphs1.7Scarce labelling and class imbalance1.8AUC-ROC, AUC-PR and top-k precision metrics1.9Building graphs from network logs1.10Workshop: NetFlow flow graph with NetworkX
2.1OddBall and egonet laws2.2Matrix factorisation and reconstruction errors2.3Community detection and membership anomalies2.4SCAN and bridge node detection2.5Random walks and personalised PageRank2.6Dense subgraph detection: Fraudar and M-Zoom2.7Isolation Forest on structural embeddings2.8Comparison of unsupervised methods2.9The PyGOD library for graph anomaly detection2.10Practical: detecting fraudulent accounts with Fraudar
3.1Embeddings with node2vec and DeepWalk3.2Graph autoencoders: DOMINANT and GAE3.3Contrastive learning: CoLA and ANEMONE3.4Supervised GNNs with imbalanced classes3.5Fraudster camouflage: CARE-GNN and PC-GNN3.6Heterogeneous graphs and metapaths3.7Explaining detected anomalies3.8Score calibration and thresholds3.9Elliptic, YelpChi and Amazon benchmarks3.10Lab: money laundering detection on the Elliptic dataset
4.1Temporal graphs and sliding windows4.2Detecting structural changes4.3SpotLight and MIDAS for streaming edges4.4Temporal Graph Networks (TGN)4.5Detecting bursts and periodic patterns4.6Latency and memory in continuous processing4.7Integration with Apache Kafka and Flink4.8Alerting and event prioritisation4.9Evaluation with labelled streams4.10Case study: scan detection in network traffic
5.1Process provenance graphs on endpoints5.2Detecting lateral movement in Active Directory5.3Attack path analysis with BloodHound5.4Threat knowledge graphs and STIX 2.15.5Technique mapping with MITRE ATT&CK5.6Detecting botnets and command and control5.7DNS graphs and malicious domains5.8Alert correlation in the SIEM5.9Reducing false positives in the SOC5.10Practical: escalation paths in a lab domain
6.1Taxonomy: evasion, poisoning and extraction6.2Structural perturbation attacks: Nettack6.3Metattack and meta-gradient poisoning6.4Fake node injection6.5Membership inference and privacy attacks6.6Defences: GNNGuard and Pro-GNN6.7Adversarial training on graphs6.8Robustness certification6.9The DeepRobust library for evaluation6.10Workshop: measuring a GCN's robustness against Nettack
7.1Integration into fraud investigation workflows7.2Explainability for analysts and auditors7.3Personal data protection in graphs7.4Anti-money laundering requirements7.5Model risk management7.6Monitoring drift and degradation7.7Graph databases: Neo4j and TigerGraph7.8Scaling with GraphFrames on Spark7.9Documentation and traceability of decisions7.10Case study: alert investigation dashboard
8.1Choosing the case: fraud or cybersecurity8.2Graph modelling and data sources8.3Baseline with classical methods8.4Deep model and tuning8.5Evaluation with imbalanced metrics8.6Adversarial robustness test8.7Designing the alert workflow8.8False positive analysis with analysts8.9Report and presentation8.10Final project: final review with the tutor
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 PyGOD, PyTorch Geometric, Neo4j Graph Data Science, BloodHound and DeepRobust, in free, academic or evaluation versions. Real procedures are studied: money laundering detection on transaction graphs, identification of lateral movement in corporate domains and robustness assessment of GNNs against perturbations. Assessment is continuous by module plus the final integrative project.
Standards covered: ISO/IEC 27001:2022, Regulation (EU) 2016/679 (GDPR), Directive (EU) 2015/849 (AML), Directive (EU) 2022/2555 (NIS2), ISO/IEC 27035, NIST SP 800-61 Rev. 2, ISO/IEC 42001:2023, Regulation (EU) 2024/1689 (AI Act).
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. 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.
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 PyGOD, PyTorch Geometric, Neo4j Graph Data Science, BloodHound and DeepRobust, 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.
Related programmes
Diploma in Drift Monitoring and Model Health
Online postgraduate diploma of 800 hours in drift monitoring and model health. 8 modules covering model degradation, statistical and sequential drift detection, label-free performance estimation, drift…
Diploma in Technical Storytelling and Dashboard Design
Online postgraduate diploma of 800 hours in technical storytelling and dashboard design, with 8 modules covering visual perception and narrative, the grammar of graphics, colour, typography…
Diploma in Uplift Modeling and Causality-Based Decision Making
Online postgraduate diploma of 800 hours in uplift modelling and causality-based decision-making. 8 modules covering potential outcomes and causal graphs, experimental design, meta-learners, causal trees and…
More in Data, AI, Simulation & Analytics
All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships