Advanced Training · DART Cybersecurity
AI Security for Engineers
A 2.5-day intensive programme equipping development and engineering professionals with the foundational knowledge to identify AI security risks, evaluate AI SaaS providers, and collaborate effectively with cybersecurity teams.
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 2.5-day course equips development and engineering professionals with the foundational knowledge needed to identify AI security risks, evaluate AI SaaS providers, and work effectively with cybersecurity teams.
Introduces how AI systems work and where risks emerge. Participants learn the differences between predictive, generative, and agentic AI; the AI supply chain (developers, deployers, operators, users); and core system components such as LLMs, prompting and reasoning methods, memory (e.g. RAG), tools, and guardrails. Concepts are grounded using hands-on exercise where participants build a simplified agentic AI system (no coding) to understand real-world architectures and attack surfaces.
Focuses on AI security threats and controls within existing cybersecurity frameworks. Participants explore OWASP Top 10 risks for LLM and generative AI, real-world AI attack scenarios, and key threat families such as prompt injection, tool/RAG abuse, and AI supply-chain attacks. Using an attack–defend approach, learners red-team and secure an agentic AI system through practical exercises, supported by case studies and MITRE ATLAS coverage. No coding or deep security background required.
The last module will focus on assessing AI SaaS vendors. Participants learn why AI vendors pose unique risks beyond traditional SaaS assessments and how to evaluate them using frameworks like CSA STAR for AI and OWASP guidance. The focus is on data handling, model and inference security, supply-chain risks, transparency, monitoring, and how to ask the right security questions and spot red flags.
Registration is Currently Closed
Registration for this course is not open at the moment. Please check back later or contact us for more information.
Contact Us