# Securing AI/ML Systems: Protecting the Intelligent Attack Surface (Self-Paced) Canonical URL: ## Overview Treat your AI and machine learning deployments as systems that have to be defended, not as a governance checkbox. This self-paced course walks the data, the model, the pipeline and the application in turn, beginning with the line between ordinary cybersecurity exposure and the exposure that belongs to AI alone, then tracing the lifecycle from first design decision to retirement and marking where a security gate belongs. A full module is given over to adversarial machine learning: how training data gets poisoned, how deployed models get fooled, how privacy attacks pull training information back out, and how models get stolen outright — each paired with the defenses that make the system harder to move against, all keyed to the NIST adversarial machine learning taxonomy, AI 100-2 E2025. Generative AI is not an afterthought here but a module of its own, working through direct and indirect prompt injection, sensitive information disclosure, insecure output handling and the damage that flows downstream, plus everything that retrieval-augmented generation, plugins, tools and outside data sources drag in with them. Two more modules go where most training simply does not. One reframes trained models, weights and checkpoints as assets that need provenance checks and change control of their own. The other confronts the AI supply chain, where a third-party model, dataset, library or framework is a dependency like any other and can be just as malicious or just as broken — a real problem, given how casually teams pull weights off public repositories compared with how they vet a software package. A closing workshop puts you in front of a fictional AI system to threat-model, with a prioritized hardening plan to argue for. This is built for whoever has to secure the thing, not whoever has to write the policy about it; if you want the awareness tier first, start with [AI Security Fundamentals for the Cyber Workforce (Self-Paced)](https://www.nobledesktop.com/classes/ai-security-fundamentals-for-the-cyber-workforce-self-paced). ## What you'll learn - Identify the components of an AI/ML system architecture and distinguish models, datasets, pipelines, applications and infrastructure - Distinguish traditional cybersecurity risk from AI-specific security risk - Map security considerations across the full AI lifecycle from design through retirement - Protect the confidentiality, integrity, availability and provenance of training and operational data - Identify data poisoning and manipulation risks across collection, labeling and preprocessing - Explain poisoning, evasion, privacy and model-extraction attacks, and apply defenses that increase robustness - Treat models, weights and checkpoints as protected assets, and verify provenance and integrity before deployment - Evaluate third-party models, datasets, libraries and frameworks as supply-chain dependencies - Identify direct and indirect prompt injection, insecure output handling, and retrieval-augmented generation risk - Secure ML pipelines, orchestration platforms, APIs and deployment processes - Detect abnormal inputs, outputs and model behavior, and distinguish performance degradation from compromise - Develop AI-specific incident response including containment, model rollback and post-incident validation ## Prerequisites Foundational knowledge of AI and machine learning systems. ## Pricing **Tuition:** $1049