OFFSEC AI-300: Advanced AI Red Teaming
About This Course
This is a 5-day intensive course designed to equip learners with the practical skills and knowledge required to assess and attack modern AI-enabled systems. Through highly hands-on training and realistic scenarios, learners explore offensive techniques targeting Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, multi-agent systems, embeddings, and supporting AI infrastructure. The course combines established red teaming methodologies with AI-specific attack techniques, enabling learners to identify vulnerabilities, understand their impact, and assess complex AI environments from an adversary’s perspective.
What You'll Learn
• Perform reconnaissance and threat detection and modeling for AI-enabled systems, identifying trust boundaries and high-value targets
• Exploit vulnerabilities in AI agents and multi-agent systems, including prompt injection and memory manipulation attacks
• Compromise RAG pipelines and vector databases through data poisoning and retrieval-layer manipulation
• Conduct embedding attacks and extract sensitive information from AI models and machine learning systems
• Exploit weaknesses in AI orchestration layers and tool integration frameworks used by modern AI applications
• Identify and exploit vulnerabilities across the AI supply chain, including datasets, models, and adapters
• Attack AI infrastructure and deployment environments, including model servers, cloud security platforms, and containerized workloads
• Perform model extraction, adversarial machine learning attacks, and AI system manipulation techniques
• Apply offensive methodology to assess AI cybersecurity risks and improve risk management strategies across AI environments
Entry Requirements
At least 3 years of working experience in cybersecurity, penetration testing, red teaming, application security, cloud security, security engineering, or related technology functions
Strong foundation in cybersecurity concepts, networking, Linux, Windows and security assessment methodologies
Familiarity with penetration testing, vulnerability assessment and offensive security concepts
Basic understanding of Artificial Intelligence (AI), Large Language Models (LLMs), Machine Learning (ML) or Generative AI concepts
Working proficiency in Microsoft Office applications (Word, Excel, PowerPoint)
Ability to speak, listen, read and write English at a proficiency level equivalent to the Employability Skills Workforce Skills Qualification (ES WSQ) Workplace Literacy (WPL) Level 6