I'm a cybersecurity engineer and MSc Cyber Security Engineering student at the University of Warwick.
My work focuses on AI security, infrastructure-as-code assurance, SOC automation, and the reliability of LLMs in security-critical decision-making.
- Evaluating LLMs as security and compliance auditors for Terraform IaC
- Benchmarking LLMs against static analysis tools such as Checkov
- Cloud security misconfiguration research using AWS CIS controls
- Detection engineering, SOC automation, and AI-assisted security workflows
- Runtime governance and policy enforcement for autonomous AI agents
A research benchmark for testing whether LLMs can safely audit Terraform configurations against AWS security controls.
Key idea:
LLMs may classify clearly misconfigured infrastructure as compliant, creating a false sense of security. I track this using an Unsafe Compliance metric.
- Cybersecurity engineering
- Incident response and SOC operations
- Cloud security and Terraform
- Infrastructure-as-code security
- LLM security and AI safety
- Detection engineering
- Python, Bash, Terraform, Sigma, Semgrep
I contribute to and build tooling around:
- IaC security checks
- LLM red-teaming and evaluation
- SOC detection rules
- Policy-as-code
- AI agent governance