ML Security and AI Red Teaming Training Course
Artificial Intelligence systems create new attack vectors such as prompt injection, data poisoning, model extraction, adversarial inputs, and supply chain compromises. While traditional application security is essential, it is not enough on its own. Securing ML requires a deep understanding of both classic vulnerabilities and AI-specific threats, including the OWASP Top 10 for LLM Applications.
This instructor-led, live training (available online or onsite) is designed for security professionals and ML engineers who need to identify, test, and defend against attacks targeting ML models and LLM-powered applications.
Upon completion of this training, participants will be able to:
- Threat-model AI systems throughout the ML lifecycle, from training to inference.
- Conduct red-team exercises against LLM applications, including testing for 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.
- Develop an AI security testing playbook for continuous validation.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and practical application.
- Hands-on implementation in a live laboratory environment.
Course Customization Options
- To request customized training, please contact us to arrange your session.
Course Outline
The AI Threat Landscape
- Why AI security differs: non-determinism, opaque reasoning, and prompts as attack surfaces.
- Attack taxonomy: training-time vs. inference-time vs. supply chain attacks.
- The ML adversary model: understanding 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 using 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 specific data was part of the training set.
- Adversarial examples: perturbations designed to fool classifiers and embeddings.
- Data poisoning: corrupting training data to induce backdoors or degrade performance.
Input and Output Security Controls
- Input sanitization strategies beyond traditional web defenses.
- Output filtering for toxicity, PII leakage, and hallucinated code execution.
- Guardrails as security infrastructure: leveraging 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 environments.
- Familiarity with security concepts including authentication, authorization, and threat modeling.
- Proficiency in Python for conducting adversarial testing exercises.
Audience
- Security engineers expanding their scope to include AI/ML threat surfaces.
- ML engineers responsible for ensuring model safety and robustness.
- Red team members adding AI systems to their testing portfolio.
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 a sophisticated framework dedicated to evaluating, overseeing, and managing security risks within artificial intelligence ecosystems.
Delivered as an instructor-led, live experience (either online or onsite), this training is specifically designed for seasoned professionals aiming to establish robust security controls and governance protocols across enterprise AI landscapes.
Upon completing this program, participants will be fully equipped to:
- Assess AI security risks by applying industry-recognized methodologies.
- Develop governance models that ensure responsible AI deployment.
- Harmonize AI security policies with broader organizational objectives and regulatory mandates.
- Strengthen resilience and foster accountability within AI-driven business operations.
Course Format
- Engaging lectures enriched with expert-led analysis.
- Hands-on workshops incorporating assessment-based learning activities.
- Practical exercises centered on real-world AI governance scenarios.
Customization Options
- For training tailored to your organization’s specific AI strategy, please reach out to us to customize the course content.
AI Governance, Compliance, and Security for Enterprise Leaders
14 HoursThis instructor-led, live training in Nigeria (online or onsite) is designed for intermediate-level enterprise leaders who wish to understand how to responsibly govern and secure AI systems in compliance with emerging global frameworks such as the EU AI Act, GDPR, ISO/IEC 42001, and the U.S. Executive Order on AI.
Upon completing this training, participants will be able to:
- Grasp the legal, ethical, and regulatory risks associated with using AI across various departments.
- Interpret and apply major AI governance frameworks, including the EU AI Act, NIST AI RMF, and ISO/IEC 42001.
- Establish security, auditing, and oversight policies for AI deployment within the enterprise.
- Develop procurement and usage guidelines for both third-party and in-house AI systems.
AI-Driven Observability: From Logs to LLM-Powered Insights
14 HoursThis instructor-led, live training in Nigeria (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 adopted to forecast incidents before they happen and to automate root cause analysis (RCA), thereby reducing downtime and speeding up resolution times.
This live, instructor-led training (available online or on-site) is designed for advanced IT professionals who want to implement predictive analytics, automate remediation processes, and design intelligent RCA workflows using AIOps tools and machine learning models.
Upon completion of this training, participants will be able to:
- Develop and train machine learning models to identify patterns that lead to system failures.
- Automate RCA workflows by correlating logs and metrics from multiple sources.
- Integrate alerting and remediation processes into existing platforms.
- Deploy and scale intelligent AIOps pipelines within production environments.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and practical practice.
- Hands-on implementation in a live lab environment.
Customization Options for the Course
- To request a customized version of this course, please contact us to make arrangements.
AIOps Fundamentals: Monitoring, Correlation, and Intelligent Alerting
14 HoursAIOps (Artificial Intelligence for IT Operations) is a discipline that leverages machine learning and advanced analytics to automate and enhance IT operations, specifically within monitoring, incident detection, and response workflows.
This instructor-led training, available both online and onsite, is designed for intermediate IT operations professionals who want to adopt AIOps techniques to correlate metrics and logs, minimize alert noise, and boost observability through intelligent automation.
Upon completion of this training, participants will be able to:
- Grasp the core principles and architecture of AIOps platforms.
- Correlate data across logs, metrics, and traces to pinpoint root causes.
- Alleviate alert fatigue via intelligent filtering and noise suppression.
- Utilize open-source or commercial tools to monitor and respond to incidents automatically.
Course Format
- Interactive lectures and discussions.
- Ample exercises and practical sessions.
- Hands-on implementation within a live-lab environment.
Customization Options
- For tailored training on this course, please reach out to us to make arrangements.
Building an AIOps Pipeline with Open Source Tools
14 HoursConstructing an AIOps pipeline entirely with open-source tools empowers teams to create flexible and cost-efficient solutions for monitoring, detecting anomalies, and managing intelligent alerts in production environments.
This instructor-led live training, available both online and onsite, targets advanced-level engineers eager to build and deploy a complete AIOps pipeline. The course utilizes tools such as Prometheus, ELK, Grafana, and custom machine learning models.
Upon completion of this training, participants will be able to:
- Architect an AIOps solution using exclusively open-source components.
- Gather and standardize data from logs, metrics, and traces.
- Implement machine learning models to identify anomalies and forecast incidents.
- Automate alerting and remediation processes using open tools.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and practical sessions.
- Hands-on implementation within a live laboratory environment.
Customization Options
- To arrange customized training for this course, kindly reach out to us.
AI Risk Management and Security in the Public Sector
7 HoursThe adoption of Artificial Intelligence (AI) brings new layers of operational risk, governance complexities, and cybersecurity vulnerabilities for government bodies and departments.
This instructor-led training, available both online and onsite, is designed for public sector IT and risk professionals who have limited experience with AI but wish to learn how to assess, monitor, and safeguard AI systems within government or regulatory environments.
Upon completing this training, participants will be equipped to:
- Understand key risk concepts associated with AI systems, such as bias, unpredictability, and model drift.
- Implement AI-specific governance and auditing frameworks, including NIST AI RMF and ISO/IEC 42001.
- Identify cybersecurity threats directed at AI models and data pipelines.
- Develop cross-departmental risk management strategies and ensure policy alignment for AI deployment.
Course Format
- Interactive lectures and discussions focusing on public sector use cases.
- Exercises involving AI governance frameworks and policy mapping.
- Scenario-based threat modeling and risk evaluation.
Customization Options
- To request a customized training session for this course, please reach out to us to make arrangements.
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 defenses 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 defenses for production environments.
Introduction to AI Trust, Risk, and Security Management (AI TRiSM)
21 HoursThis guided, live training session in Nigeria (available online or in-person) is designed for IT professionals at beginner to intermediate levels who want to learn how to apply AI TRiSM principles within their organisations.
Upon completing this training, participants will be able to:
- Understand the fundamental concepts and significance of managing trust, risk, and security in AI.
- Detect and address risks linked to AI systems.
- Apply security best practices specific to AI.
- Gain insight into regulatory compliance and ethical issues concerning AI.
- Formulate strategies for robust AI governance and management.
Autonomous Operations with AI Agents
14 HoursThis instructor-led, live training in Nigeria (online or onsite) is designed for SRE and DevOps engineers who wish 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 Nigeria (online or onsite) is aimed at intermediate-level to advanced-level AI developers, architects, and product managers who wish to identify and mitigate risks associated with LLM-powered applications, including prompt injection, data leakage, and unfiltered output, while incorporating security controls like input validation, human-in-the-loop oversight, and output guardrails.
By the end of this training, participants will be able to:
- Understand the core vulnerabilities of LLM-based systems.
- Apply secure design principles to LLM app architecture.
- Use tools such as Guardrails AI and LangChain for validation, filtering, and 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 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-grade AIOps platforms such as Splunk, Moogsoft, and Dynatrace offer robust capabilities for identifying anomalies, correlating alerts, and automating responses within large-scale IT environments.
This instructor-led training, available both online and onsite, 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 equipped 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 through built-in and custom workflows.
- Enhance performance, reduce MTTR, and boost operational efficiency at an enterprise scale.
Course Format
- Interactive lectures and discussions.
- Numerous exercises and practical sessions.
- Hands-on implementation in a live-lab environment.
Customization Options
- To request a customized version of this course, please contact us to arrange.
Implementing AIOps with Prometheus, Grafana, and ML
14 HoursPrometheus and Grafana are industry-standard tools for ensuring observability within modern infrastructure, while machine learning elevates these platforms by providing predictive and intelligent insights to automate operational decisions.
This instructor-led live training (available online or on-site) is designed for observability professionals at an intermediate level who aim to modernize their monitoring systems by integrating AIOps methodologies using Prometheus, Grafana, and machine learning techniques.
Upon completion of this training, participants will be able to:
- Configure Prometheus and Grafana to achieve comprehensive observability across various systems and services.
- Collect, store, and visualize high-quality time series data effectively.
- Deploy machine learning models for the purposes of anomaly detection and forecasting.
- Develop intelligent alerting rules derived from predictive insights.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and practical practice sessions.
- Hands-on implementation within a live laboratory environment.
Course Customization Options
- To request a customized training session for this course, please contact us to make arrangements.
LLMOps: Production LLM Operations and Governance
14 HoursThis instructor-led, live training in Nigeria (online or onsite) is aimed at ML engineers and platform teams who need to build robust operational pipelines for LLM-powered applications at scale.
