Advanced Training · DART Cybersecurity
AI for Cybersecurity Professionals
A 5-day intensive programme equipping cybersecurity leadership and governance teams with the skills to assess, secure, and oversee AI systems.
As AI systems become increasingly integrated into government operations, they present evolving security challenges that require dedicated attention from cybersecurity leadership. The rapid adoption of AI has created a critical gap: while these systems are fundamentally software that should follow well-established cybersecurity practices, their unique characteristics demand new approaches to risk assessment, threat modelling, and security controls.
AI systems possess distinctive properties that differentiate them from traditional software and create novel security vulnerabilities. They are dynamic and adaptive, learning and changing behavior based on data and interactions, making vulnerabilities harder to identify and contain. They perform complex tasks at unprecedented scale with reduced human oversight, meaning security failures can have amplified impacts across entire organizations. Most critically, LLM-based applications suffer from a fundamental design vulnerability – instructions and data are passed on the same channel – creating opportunities for prompt injection and model extraction. This, together with other AI-related attacks such as data poisoning and adversarial examples, creates threats that traditional security controls were not designed to address.
Meanwhile, adversaries are actively targeting AI systems as high-value assets, seeking to extract proprietary models, poison training data, manipulate outputs, and exploit the trust organizations place in AI-driven decisions. This creates an urgent need for cybersecurity professionals who can integrate AI-specific risks into their threat models, develop appropriate controls and mitigations, and build incident response capabilities for AI security breaches.
This training program is designed to equip practitioners with the hands-on knowledge needed to assess, manage, and mitigate security risks in AI systems, building capabilities in understanding AI system architecture, integrating AI-specific threats into risk assessments, implementing security controls across the AI lifecycle, and developing organizational strategies for AI security governance.
This course is designed for professionals responsible for:
The first part of the training introduces participants to the modern AI landscape, clarifying the differences between predictive AI, generative AI, and agentic AI, and how each creates distinct security considerations. Learners explore the full AI supply chain, including the roles of developers, deployers, operators, and users, as well as the critical resources involved such as models, data, software frameworks, hardware infrastructure, and compute.
Participants also study the core building blocks of AI systems, including LLM architectures, prompting and reasoning methods, memory and Retrieval-Augmented Generation (RAG), and tool integration through function calling and protocols like MCP. The module is highly hands-on: learners progressively build a simplified agentic AI system in n8n (no coding) to understand how real-world AI deployments expand attack surfaces and security risks.
The module examines the threat landscape for AI systems and how effective security controls can be designed and integrated into existing cybersecurity programs. Participants learn how AI-enabled applications inherit traditional software vulnerabilities while introducing new attack vectors unique to generative and agentic AI. The OWASP Top 10 for LLM and Generative AI applications is used as a foundation, supported by real-world examples that highlight common risks and practical mitigations.
Key AI threat families—including prompt injection, tool and RAG abuse, and AI supply chain attacks—are explored alongside broader techniques documented in MITRE ATLAS. Each area is approached using an Attack–Defend–Validate method, where participants analyse vulnerabilities, design defensive controls, and validate mitigations in realistic scenarios. Exercises require no coding and focus on security decision-making rather than attack execution, reinforced through recent case studies and large-scale government deployment examples.
The module focuses on AI governance, risk, and compliance, and on applying threat modeling to AI systems. Participants explore the MITRE ATLAS framework to understand adversary tactics targeting AI and engage with the NIST AI Risk Management Framework (AI RMF) to identify, assess, and govern AI risks, including considerations such as bias, transparency, privacy, and safety. The session also introduces key organizational controls, including AI Bills of Materials (AIBOM), model registries, and governance approaches for managing employee adoption and use of external AI tools.
The module addresses how to respond to and investigate AI security incidents. Participants learn to identify indicators of compromise in AI systems, conduct forensic analysis of AI security breaches (including log analysis, data poisoning detection, and prompt injection traces), contain and remediate AI-specific security incidents, and document findings for post-incident review. The session builds on traditional incident response frameworks while addressing AI-specific investigation challenges such as non-deterministic behavior, distributed attack surfaces, and contaminated training or retrieval data.
Registration Received!
Thank you for your interest in AI for Cybersecurity Professionals.
Our team will be in touch with your acceptance confirmation and invoice details.
Questions? Email [email protected]