How to implement an AI Software Bill of Materials capturing base models, adapters, training datasets, and dependencies — and use it for supply chain risk and compliance.
Defensive Techniques
Practical architectures, frameworks, and controls to secure AI systems in production.
A practical framework for implementing prompt injection detection at the API gateway layer: input sanitisation, context isolation, output filtering, and anomaly detection.
Applying zero trust to ML infrastructure: training pipeline access controls, model registry security, inference endpoint hardening, and secrets management for AI deployments.
Design patterns for a prompt injection and jailbreak detection layer: rule-based filters, semantic classifiers, canary tokens, and output validation for production LLMs.
A structured methodology for red teaming LLM applications: attack taxonomy, scoping, tooling (Garak, PyRIT, PromptBench), and translating findings into actionable security controls.