ML Security and AI Red Teaming Training Course
AI systems introduce novel attack surfaces: prompt injection, data poisoning, model extraction, adversarial inputs, and supply chain compromises. Traditional application security is necessary but insufficient. ML security requires understanding both classic vulnerability classes and AI-specific threats including the OWASP Top 10 for LLM Applications.
This instructor-led, live training (online or onsite) is aimed at security and ML engineers who need to identify, test, and defend against attacks on ML models and LLM-powered applications.
By the end of this training, participants will be able to:
- Threat-model AI systems across the ML lifecycle from training to inference.
- Execute red-team exercises against LLM applications including prompt injection and jailbreak attempts.
- Detect and defend against data poisoning, model extraction, and membership inference attacks.
- Apply the OWASP Top 10 for LLM Applications to real-world deployments.
- Implement input validation, output filtering, and guardrail strategies.
- Conduct supply chain security assessments for model artifacts and dependencies.
- Build an AI security testing playbook for continuous validation.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training, please contact us to arrange.
Course Outline
The AI Threat Landscape
- Why AI security is different: non-determinism, opaque reasoning, prompt as attack surface
- Attack taxonomy: training-time vs inference-time vs supply chain attacks
- The ML adversary model: who attacks AI systems and why
OWASP Top 10 for LLM Applications
- Prompt injection: direct and indirect attack vectors
- Insecure output handling and cross-plugin request forgery
- Training data poisoning and supply chain vulnerabilities
- Model denial of service, sensitive information disclosure, and excessive agency
- Hands-on lab: exploiting each OWASP category against a test application
Prompt Injection and Jailbreak Red Teaming
- Taxonomy of injection techniques: direct, indirect, multi-turn, and multi-modal
- Automated red-teaming with Giskard, Garak, and custom fuzzing tools
- Jailbreak classification and defense evaluation
- Building a red-team harness for continuous LLM security testing
Model-Level Attacks and Defenses
- Model extraction: stealing model weights and functionality via API queries
- Membership inference: determining if data was in the training set
- Adversarial examples: perturbations that fool classifiers and embeddings
- Data poisoning: corrupting training data to induce backdoors or degrade performance
Input and Output Security Controls
- Input sanitization beyond traditional web defenses
- Output filtering: toxicity, PII leakage, hallucinated code execution
- Guardrails as security infrastructure: NeMo, Guardrails AI, and custom policies
- Structured output enforcement as a security boundary
AI Supply Chain Security
- Model provenance: verifying model authenticity and integrity
- Dependency scanning for ML frameworks and model formats
- Secure model serving: sandboxing, network isolation, and least-privilege access
- Vetting fine-tuned and community models for embedded malware
Operational Security for AI Systems
- Access control for model endpoints, vector stores, and agent tools
- Audit logging for every model interaction and decision
- Incident response for AI-specific breaches: when the model itself is compromised
- Continuous security testing in CI/CD for ML pipelines
Building an AI Security Program
- AI security maturity model and roadmap
- Integrating AI security into existing AppSec and cloud security programs
- Governance frameworks and emerging regulations for AI systems
- Creating and maintaining an organizational AI security playbook
Requirements
- Experience deploying ML models or LLM applications in production.
- Familiarity with security concepts including authentication, authorization, and threat modeling.
- Python proficiency for adversarial testing exercises.
Audience
- Security engineers expanding into AI/ML threat surfaces.
- ML engineers responsible for model safety and robustness.
- Red team members adding AI systems to their testing scope.
Need help picking the right course?
southafrica@nobleprog.co.za or +27 (0)10 005 5793
ML Security and AI Red Teaming Training Course - Enquiry
Related Courses
ISACA Advanced in AI Security Management (AAISM)
21 HoursAAISM serves as an advanced framework designed for assessing, governing, and managing security risks within artificial intelligence systems.
This instructor-led, live training (available online or onsite) is tailored for advanced-level professionals seeking to implement effective security controls and governance practices for enterprise AI environments.
Upon completion of this program, participants will be equipped to:
- Evaluate AI security risks using industry-recognized methodologies.
- Implement governance models for responsible AI deployment.
- Align AI security policies with organizational goals and regulatory expectations.
- Enhance resilience and accountability within AI-driven operations.
Format of the Course
- Facilitated lectures supported by expert analysis.
- Practical workshops and assessment-based activities.
- Applied exercises using real-world AI governance scenarios.
Course Customization Options
- For tailored training aligned to your organizational AI strategy, please contact us to customize the course.
AI Governance, Compliance, and Security for Enterprise Leaders
14 HoursThis instructor-led, live training in Botswana (online or onsite) is aimed at intermediate-level enterprise leaders who wish to understand how to govern and secure AI systems responsibly and in compliance with emerging global frameworks such as the EU AI Act, GDPR, ISO/IEC 42001, and the U.S. Executive Order on AI.
By the end of this training, participants will be able to:
- Understand the legal, ethical, and regulatory risks of using AI across departments.
- Interpret and apply major AI governance frameworks (EU AI Act, NIST AI RMF, ISO/IEC 42001).
- Establish security, auditing, and oversight policies for AI deployment in the enterprise.
- Develop procurement and usage guidelines for third-party and in-house AI systems.
AI-Driven Observability: From Logs to LLM-Powered Insights
14 HoursThis instructor-led, live training in Botswana (online or onsite) is aimed at observability and SRE engineers who want to integrate LLMs and AI into their monitoring, alerting, and incident analysis workflows.
AIOps in Action: Incident Prediction and Root Cause Automation
14 HoursAIOps (Artificial Intelligence for IT Operations) is increasingly being used to predict incidents before they occur and automate root cause analysis (RCA) to minimize downtime and accelerate resolution.
This instructor-led, live training (online or onsite) is aimed at advanced-level IT professionals who wish to implement predictive analytics, automate remediation, and design intelligent RCA workflows using AIOps tools and machine learning models.
By the end of this training, participants will be able to:
- Build and train ML models to detect patterns leading to system failures.
- Automate RCA workflows based on multi-source log and metric correlation.
- Integrate alerting and remediation processes into existing platforms.
- Deploy and scale intelligent AIOps pipelines in production environments.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
AIOps Fundamentals: Monitoring, Correlation, and Intelligent Alerting
14 HoursAIOps (Artificial Intelligence for IT Operations) represents a methodology that leverages machine learning and analytics to automate and enhance IT operations, with a specific focus on monitoring, incident detection, and response.
This instructor-led, live training—available either online or on-site—is designed for intermediate-level IT operations professionals seeking to implement AIOps techniques. Participants will learn to correlate metrics and logs, minimize alert noise, and boost observability through intelligent automation.
Upon completion of this training, participants will be equipped to:
- Grasp the core principles and architecture of AIOps platforms.
- Correlate data across logs, metrics, and traces to pinpoint root causes.
- Mitigate alert fatigue by employing intelligent filtering and noise suppression techniques.
- Utilize both open-source and commercial tools to automatically monitor and respond to incidents.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and practical practice sessions.
- Hands-on implementation within a live-lab environment.
Course Customization Options
- For requests regarding customized training for this course, please contact us to make arrangements.
Building an AIOps Pipeline with Open Source Tools
14 HoursImplementing an AIOps pipeline composed entirely of open-source tools empowers teams to create cost-efficient and adaptable solutions for monitoring, identifying anomalies, and managing intelligent alerts within production systems.
This instructor-led live training, available online or onsite, is tailored for advanced engineers looking to develop and deploy a comprehensive AIOps pipeline utilizing tools such as Prometheus, ELK, Grafana, and custom machine learning models.
Upon completing this training, participants will be equipped to:
- Architect an AIOps system using exclusively open-source components.
- Gather and standardize data from logs, metrics, and traces.
- Utilise ML models to detect anomalies and forecast incidents.
- Automate alerting and remediation processes using open tooling.
Course Format
- Interactive lectures and discussions.
- Numerous exercises and practical activities.
- Hands-on implementation within a live-lab environment.
Customisation Options
- To request a tailored training session for this course, please contact us to make arrangements.
AI Risk Management and Security in the Public Sector
7 HoursArtificial Intelligence (AI) introduces new dimensions of operational risk, governance challenges, and cybersecurity exposure for government agencies and departments.
This instructor-led, live training (online or onsite) is aimed at public sector IT and risk professionals with limited prior experience in AI who wish to understand how to evaluate, monitor, and secure AI systems within a government or regulatory context.
By the end of this training, participants will be able to:
- Interpret key risk concepts related to AI systems, including bias, unpredictability, and model drift.
- Apply AI-specific governance and auditing frameworks such as NIST AI RMF and ISO/IEC 42001.
- Recognize cybersecurity threats targeting AI models and data pipelines.
- Establish cross-departmental risk management plans and policy alignment for AI deployment.
Format of the Course
- Interactive lecture and discussion of public sector use cases.
- AI governance framework exercises and policy mapping.
- Scenario-based threat modeling and risk evaluation.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
AI Security for Security Teams
35 HoursThis course provides a practical introduction to securing modern AI-powered applications, APIs, copilots, and autonomous agents. Participants learn how AI security differs from traditional web security, explore common AI-specific threats such as prompt injection, RAG poisoning, and agent abuse, and understand how to protect AI systems using layered defences including WAFs, AI gateways, API security, and guardrails. Through hands-on labs and real-world examples, students gain the skills to identify AI attack patterns, secure LLM-based applications, and deploy effective runtime defences for production environments.
Introduction to AI Trust, Risk, and Security Management (AI TRiSM)
21 HoursThis instructor-led, live training in Botswana (online or onsite) is aimed at beginner-level to intermediate-level IT professionals who wish to understand and implement AI TRiSM in their organizations.
By the end of this training, participants will be able to:
- Grasp the key concepts and importance of AI trust, risk, and security management.
- Identify and mitigate risks associated with AI systems.
- Implement security best practices for AI.
- Understand regulatory compliance and ethical considerations for AI.
- Develop strategies for effective AI governance and management.
Autonomous Operations with AI Agents
14 HoursThis instructor-led, live training in Botswana (online or onsite) is aimed at SRE and DevOps engineers who want to design, build, and safely deploy AI agents for autonomous IT operations.
Building Secure and Responsible LLM Applications
14 HoursThis instructor-led, live training in Botswana (online or onsite) is designed for intermediate to advanced AI developers, architects, and product managers who wish to identify and mitigate risks associated with LLM-powered applications, such as prompt injection, data leakage, and unfiltered output. The course covers the integration of security controls like input validation, human-in-the-loop oversight, and output guardrails.
By the conclusion of this training, participants will be able to:
- Grasp the core vulnerabilities inherent in LLM-based systems.
- Apply secure design principles to the architecture of LLM applications.
- Utilise tools such as Guardrails AI and LangChain for validation, filtering, and ensuring safety.
- Integrate techniques like sandboxing, red teaming, and human-in-the-loop review into production-grade pipelines.
Building Secure AI Applications
21 HoursThis course teaches software developers how to build AI-powered applications securely by design. Participants learn how to protect chatbots, copilots, RAG pipelines, and AI agents against AI-specific threats such as prompt injection, data poisoning, tool abuse, secret leakage, and insecure model output. The course covers secure prompt design, RAG security, least-privilege access, guardrails, and red-team testing, helping developers build AI features that are secure, reliable, and resilient in real-world environments.
Enterprise AIOps with Splunk, Moogsoft, and Dynatrace
14 HoursEnterprise AIOps platforms such as Splunk, Moogsoft, and Dynatrace offer robust capabilities for identifying anomalies, linking alerts, and automating responses across extensive IT environments.
This instructor-led live training, available online or on-site, is designed for intermediate-level enterprise IT teams looking to integrate AIOps tools into their current observability stacks and operational workflows.
Upon completing this training, participants will be able to:
- Configure and integrate Splunk, Moogsoft, and Dynatrace into a cohesive AIOps architecture.
- Correlate metrics, logs, and events across distributed systems using AI-driven analysis.
- Automate incident detection, prioritization, and response using both built-in and custom workflows.
- Enhance performance, reduce MTTR, and improve operational efficiency at an enterprise scale.
Course Format
- Interactive lectures and discussions.
- Numerous exercises and practical activities.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Implementing AIOps with Prometheus, Grafana, and ML
14 HoursPrometheus and Grafana are widely embraced tools for ensuring observability in contemporary infrastructure, while machine learning augments these platforms with predictive and intelligent insights to automate operational decisions.
This instructor-led, live training (available online or on-site) targets intermediate-level observability professionals seeking to modernise their monitoring infrastructure by integrating AIOps practices through the use of Prometheus, Grafana, and ML techniques.
Upon completion of this training, participants will be able to:
- Configure Prometheus and Grafana to provide observability across various systems and services.
- Collect, store, and visualise high-quality time series data.
- Apply machine learning models for anomaly detection and forecasting.
- Develop intelligent alerting rules grounded in predictive insights.
Format of the Course
- Interactive lectures and discussions.
- Extensive exercises and practical sessions.
- Hands-on implementation within a live laboratory environment.
Course Customisation Options
- To request customised training for this course, please contact us to arrange.
LLMOps: Production LLM Operations and Governance
14 HoursThis instructor-led, live training in Botswana (online or onsite) is aimed at ML engineers and platform teams who need to build robust operational pipelines for LLM-powered applications at scale.
