I work at the intersection of cybersecurity, artificial intelligence, threat intelligence, privacy, and digital health security, with a growing focus on building trustworthy and explainable AI systems for security-sensitive environments.
I bring 4+ years of cybersecurity experience spanning SOC operations, digital forensics and incident response, threat intelligence, security governance, risk and compliance.
Alongside my professional work, I build open-source security and AI projects and conduct applied research around trustworthy AI, AI security, cybersecurity governance, explainable systems, and secure digital health technologies.
Released ExploitLattice v1.0.0, an open-source attack-path-aware secure code review framework for AI-assisted security work. It combines evidence-gated findings, attack-path chaining, reachability-aware prioritisation and remediation choke-point analysis.
Explore ExploitLattice · View v1.0.0 Release
Built an open, source-traceable evidence infrastructure for documenting AI incidents affecting African people, institutions and information environments.
The seed dataset contains 17 curated incidents across 9 primary African countries, supported by evidence-confidence grading, transparent impact scoring, provenance tracking and a public interactive explorer.
Explore the Observatory · Live Dashboard
Africa's AI Failures Are Hiding in Plain Sight: I Built a Dataset to Track Them
A public-facing analysis of why AI harms affecting African societies can remain fragmented and poorly documented — and how structured incident evidence can support stronger AI governance, accountability and research.
- Trustworthy & Explainable AI
- AI Security & Adversarial AI
- Cyber Threat Intelligence
- Digital Health & Healthcare Cybersecurity
- Privacy & Data Governance
- Cybersecurity Governance & Risk Management
- Human-Centred Security
- Security Operations & Incident Response
- Responsible AI for High-Risk Systems
Attack-path-aware secure code review for AI-assisted security work.
ExploitLattice is an open-source security-review framework and deterministic attack-path helper that moves beyond flat vulnerability lists to identify how individual weaknesses can connect into credible attacker paths — and which remediation can break the most dangerous path first.
The v1.0.0 public release introduces evidence-gated findings, attack-path chaining, reachability-aware prioritisation, remediation choke points, secure patch guidance, regression validation, and mappings to OWASP Top 10:2025, OWASP ASVS, CWE and CVSS v4.0.
Focus: Application Security • Attack Paths • Secure Code Review • AI-Assisted Security • DevSecOps • Security Engineering
View Repository · View v1.0.0 Release
Open evidence infrastructure for documenting AI incidents affecting African people, institutions and information environments.
AAIO addresses a visibility gap in global AI governance by converting fragmented public reporting into structured, source-traceable incident evidence.
The observatory incorporates explicit inclusion criteria, source provenance, evidence-confidence grading, transparent impact scoring, a conservative watchlist for uncertain AI causation, automated data validation and a searchable public dashboard.
Its seed release documents 17 curated incidents across 9 primary African countries, creating an auditable foundation for research into AI harms, governance and accountability in African contexts.
Focus: AI Governance • AI Safety • Responsible AI • Incident Intelligence • Africa • Public-Interest Technology
Live Observatory · Dataset & Source
Privacy-first, explainable security-log triage for SOC analysts and incident responders.
TriageBloom provides deterministic security triage with ATT&CK-aligned detections, evidence traceability, pseudonymisation and analyst-readable reporting.
Focus: SOC Automation • Explainable Security • Threat Detection • DFIR • MITRE ATT&CK
Research prototype for detecting clinically significant information drift in AI-transformed health records.
ClinDrift explores evidence-traceable detection of safety-relevant changes in clinical information, with human-review safeguards designed for trustworthy AI-enabled healthcare environments.
Focus: Digital Health • Trustworthy AI • Clinical AI Safety • Information Integrity
Evidence intelligence for cybersecurity, privacy and regulatory readiness.
BGNexa-AI explores structured AI-assisted evidence analysis for security assessments, compliance workflows, control validation and governance decision-making.
Focus: AI Governance • GRC • Cybersecurity Assurance • Evidence Intelligence
My current research explores the convergence of AI, cybersecurity, digital health and governance, with particular interest in how AI-enabled systems can remain secure, explainable and trustworthy in high-risk environments.
Current and developing research themes include:
- AI-driven cybersecurity for electronic health records
- Zero Trust and AI-based risk management in digital health
- Trustworthy agentic AI for cybersecurity
- Explainable AI for cyber threat intelligence
- Human factors and adoption of privacy-enhancing technologies
- Security governance for AI-enabled healthcare systems
- Explainable and privacy-preserving security triage
- AI incident monitoring and evidence infrastructure in African contexts
Medium • 2026
An analysis of the visibility and evidence gap surrounding AI incidents in African contexts and the need for stronger public-interest infrastructure for documenting AI harms.
The article introduces the motivation behind the Africa AI Incident Observatory, connecting open data, incident documentation and source provenance with wider questions of AI governance and accountability.
Themes: AI Governance • Responsible AI • AI Safety • Africa • Technology Policy • Incident Evidence
Presented at AISEC 2026 • Marrakech, Morocco
Research examining the use of explainable AI approaches to improve cyber threat intelligence reporting and support more interpretable security decision-making across African organisations.
Themes: Explainable AI • Cyber Threat Intelligence • African Cybersecurity • Security Operations
My developing research spans:
- Trustworthy and adversarial AI for cybersecurity
- AI-driven cybersecurity for electronic health records
- Zero Trust and AI-based risk management in digital health
- AI governance and security assurance
- Human factors and privacy-enhancing technologies
- Explainable and privacy-preserving security triage
- AI incident monitoring and evidence infrastructure in African contexts
Where appropriate, research artefacts, datasets and reproducible implementations are released publicly through my GitHub repositories.
I contribute to cybersecurity education and professional knowledge sharing through:
- Cybersecurity conference and industry presentations
- Threat intelligence and SOC training
- Digital forensics and incident-response education
- AI security and governance discussions
- Cybersecurity mentoring and workshops
My speaking interests include:
Threat Intelligence • SOC & DFIR • AI Security • Cybersecurity Governance • Digital Health Security
My cybersecurity experience spans:
Threat Intelligence
SOC Operations
Digital Forensics & Incident Response
Security Governance, Risk & Compliance
Security Monitoring & Threat Hunting
MITRE ATT&CK
OSINT
AI Security
Digital Health Security
I currently work in cybersecurity while pursuing advanced study and research in artificial intelligence.
I am currently building and researching systems around:
- Explainable security automation
- AI-assisted cybersecurity evidence analysis
- Trustworthy AI for digital health
- AI governance and security assurance
- AI incident monitoring and public-interest evidence infrastructure
- Reproducible cybersecurity research
I am particularly interested in PhD research and research collaborations involving cybersecurity, trustworthy AI, digital health security, privacy, and AI governance.
I am open to collaboration in:
- Cybersecurity and AI research
- Trustworthy and Responsible AI
- Digital Health Security
- Cyber Threat Intelligence
- AI Governance
- AI Incident Monitoring
- Privacy and Security Engineering
- Open-Source Security Research
Research & collaboration: Cybersecurity • Trustworthy AI • AI Security • Digital Health Security • Threat Intelligence • AI Governance
Building trustworthy, explainable and secure systems at the intersection of cybersecurity, AI governance and high-risk digital environments.