Red Teaming - Sparring & Support

What you will learn about Red Teaming

• Intro & Red Teaming Fundamentals
  Core concepts of red teaming, ethics, scope, and rules for safe, controlled testing
• Framing & Safety Fundamentals
  Threat modeling & scoping, rules of engagement; safe handling of data (PII/secrets); measurable success criteria for each run
• LLM Jailbreaking – Core Techniques
  Overview of prompt injection & jailbreak patterns, plus tool/permission abuse (conceptual tactics, no exploit how-tos)
• Advanced Attacks
  Multi-turn tactics, multimodal risks (text/image/audio), converter vectors (format & channel switching), and other current patterns; typical detection signals
• Automation & Metrics – Prompt Sets, Replay Harness & Scoring
  Evaluation rubrics, regression suites, comparability across runs/models
• Defense, Detection & Reporting – Guardrails
  Policies (input and output controls, approval gates), AI compliance (e.g., EU AI Act/GDPR/Swiss FADP), reporting (risk rating, evidence, executive summary) & mitigation planning (short-, mid-, long-term roadmap)
  

After this course, your business and tech teams will better understand:

• AI security fundamentals

• Agentic AI fundamentals

• Prompt Injection & Jailbreaks – How users can trick an AI into ignoring its rules and doing things it should not do
• RAG Poisoning – How false or manipulated documents are injected into a system’s knowledge base to produce wrong answers
• Data Exfiltration – How sensitive data can be leaked through an AI system without being noticed

• PII Leakage – When an AI exposes personal data that should be protected
• Tool & Function-Call Abuse – When an AI is manipulated into executing connected tools or systems in dangerous ways
• Insecure Output Handling – When AI responses are used without being checked for risks such as code, commands, or sensitive content
• Long-Context Contamination – A security and quality issue where earlier or hidden inputs in long contexts push the model into unsafe, incorrect, or manipulable behavior
• Cost Abuse & Denial of Service (DoS) – When an AI system is flooded with requests to drive up costs or make it unavailable

• Hallucination Induction – Techniques that deliberately cause an AI to generate convincing but false information

How we work

1. Scoping & Threat Model - Objectives, protection needs, architecture, data flows, policies.
2. Attack Simulation - Manual exploits, automated red-team agents, fuzzing & scenario testing (prod-like in a safe sandbox).
3. Purple-Team Fix Sprint - Joint hardening: RAG controls, tool safeguards, guardrails, prompt & policy design, safe output handling.
4. Report, Retest & Enablement - Action plan, KPIs, go-live gates, runbook, training.

We build agentic end-to-end automation every day, test chatbots and agents, so we know where it breaks in the real world. We want to share this valuable experiences with you.

Our promise: hands-on, measurable risk reduction, and awareness of the risks and migitation methods that exist.