Cybersecurity in AI Systems Training Course
Securing AI systems presents unique challenges that differ from traditional cybersecurity approaches. AI systems are vulnerable to adversarial attacks, data poisoning, and model theft, all of which can significantly impact business operations and data integrity. This course explores key cybersecurity practices for AI systems, covering adversarial machine learning, data security in machine learning pipelines, and compliance requirements for robust AI deployment.
This instructor-led, live training (online or onsite) is aimed at intermediate-level AI and cybersecurity professionals who wish to understand and address the security vulnerabilities specific to AI models and systems, particularly in highly regulated industries such as finance, data governance, and consulting.
By the end of this training, participants will be able to:
- Understand the types of adversarial attacks targeting AI systems and methods to defend against them.
- Implement model hardening techniques to secure machine learning pipelines.
- Ensure data security and integrity in machine learning models.
- Navigate regulatory compliance requirements related to AI security.
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.
Course Outline
Introduction to AI Security Challenges
- Understanding security risks unique to AI systems
- Comparing traditional cybersecurity vs. AI cybersecurity
- Overview of attack surfaces in AI models
Adversarial Machine Learning
- Types of adversarial attacks: evasion, poisoning, and extraction
- Implementing adversarial defenses and countermeasures
- Case studies on adversarial attacks in different industries
Model Hardening Techniques
- Introduction to model robustness and hardening
- Techniques for reducing model vulnerability to attacks
- Hands-on with defensive distillation and other hardening methods
Data Security in Machine Learning
- Securing data pipelines for training and inference
- Preventing data leakage and model inversion attacks
- Best practices for managing sensitive data in AI systems
AI Security Compliance and Regulatory Requirements
- Understanding regulations around AI and data security
- Compliance with GDPR, CCPA, and other data protection laws
- Developing secure and compliant AI models
Monitoring and Maintaining AI System Security
- Implementing continuous monitoring for AI systems
- Logging and auditing for security in machine learning
- Responding to AI security incidents and breaches
Future Trends in AI Cybersecurity
- Emerging techniques in securing AI and machine learning
- Opportunities for innovation in AI cybersecurity
- Preparing for future AI security challenges
Summary and Next Steps
Requirements
- Basic knowledge of machine learning and AI concepts
- Familiarity with cybersecurity principles and practices
Audience
- AI and machine learning engineers looking to improve security in AI systems
- Cybersecurity professionals focusing on AI model protection
- Compliance and risk management professionals in data governance and security
Need help picking the right course?
southafrica@nobleprog.co.za or +27 (0)10 005 5793
Cybersecurity in AI Systems Training Course - Enquiry
Testimonials (1)
The profesional knolage and the way how he presented it before us
Miroslav Nachev - PUBLIC COURSE
Course - Cybersecurity in AI Systems
Upcoming Courses
Related Courses
ISACA Advanced in AI Security Management (AAISM)
21 HoursAAISM serves as an advanced framework designed for the assessment, governance, and management of security risks associated with artificial intelligence systems.
This instructor-led live training, available online or onsite, targets advanced-level professionals who aim to establish effective security controls and governance practices within enterprise AI environments.
Upon completing this program, participants will be equipped to:
- Evaluate security risks related to AI using industry-recognized methodologies.
- Implement governance models that support the responsible deployment of AI.
- Align AI security policies with both organizational objectives and regulatory expectations.
- Strengthen resilience and accountability in AI-driven operations.
Format of the Course
- Facilitated lectures complemented by expert analysis.
- Practical workshops and assessment-based activities.
- Applied exercises utilising real-world AI governance scenarios.
Course Customization Options
- For bespoke training that aligns with 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 South Africa (online or onsite) is designed for intermediate-level enterprise leaders seeking to comprehend how to govern and secure AI systems responsibly, ensuring compliance with emerging global frameworks such as the EU AI Act, GDPR, ISO/IEC 42001, and the U.S. Executive Order on AI.
Upon completion of 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 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.
Introduction to AI Trust, Risk, and Security Management (AI TRiSM)
21 HoursThis instructor-led, live training in South Africa (online or onsite) is aimed at beginner to intermediate IT professionals who wish to understand and implement AI TRiSM in their organisations. <\/p>
By the end of this training, participants will be able to: <\/p>
- Comprehend the core concepts and significance of AI trust, risk, and security management. <\/li>
- Identify and mitigate risks linked to AI systems. <\/li>
- Apply security best practices for AI. <\/li>
- Gain insight into regulatory compliance and ethical considerations for AI. <\/li>
- Develop strategies for effective AI governance and management. <\/li> <\/ul>
Building Secure and Responsible LLM Applications
14 HoursThis instructor-led, live training in South Africa (online or onsite) is designed for intermediate to advanced AI developers, architects, and product managers who aim to identify and mitigate risks linked to LLM-powered applications. These risks include prompt injection, data leakage, and unfiltered outputs, while incorporating security controls such as input validation, human-in-the-loop oversight, and output guardrails.
Upon completion of this training, participants will be able to:
- Grasp the core vulnerabilities inherent in LLM-based systems.
- Apply secure design principles to LLM application architecture.
- Utilise tools like Guardrails AI and LangChain for validation, filtering, and ensuring safety.
- Integrate techniques such as sandboxing, red teaming, and human-in-the-loop review into production-grade pipelines.
EXO Security and Governance: Offline Model Management
14 HoursThis instructor-led, live training in South Africa (online or onsite) is aimed at security engineers and compliance officers who wish to harden EXO deployments, control model access, and govern AI workloads running entirely on-premise.
Introduction to AI Security and Risk Management
14 HoursThis instructor-led live training in South Africa (online or onsite) is aimed at beginner-level IT security, risk, and compliance professionals who wish to understand foundational AI security concepts, threat vectors, and global frameworks such as NIST AI RMF and ISO/IEC 42001.
By the end of this training, participants will be able to:
- Understand the unique security risks introduced by AI systems.
- Identify threat vectors such as adversarial attacks, data poisoning, and model inversion.
- Apply foundational governance models like the NIST AI Risk Management Framework.
- Align AI use with emerging standards, compliance guidelines, and ethical principles.
OWASP GenAI Security
14 HoursBased on the latest OWASP GenAI Security Project guidance, participants will learn to identify, assess, and mitigate AI-specific threats through hands-on exercises and real-world scenarios.
Privacy-Preserving Machine Learning
14 HoursThis instructor-led, live training in South Africa (online or onsite) is aimed at advanced-level professionals who wish to implement and evaluate techniques such as federated learning, secure multiparty computation, homomorphic encryption, and differential privacy in real-world machine learning pipelines.
By the end of this training, participants will be able to:
- Understand and compare key privacy-preserving techniques in ML.
- Implement federated learning systems using open-source frameworks.
- Apply differential privacy for safe data sharing and model training.
- Use encryption and secure computation techniques to protect model inputs and outputs.
Red Teaming AI Systems: Offensive Security for ML Models
14 HoursThis instructor-led, live training in South Africa (online or onsite) targets advanced security professionals and machine learning specialists who wish to simulate attacks on AI systems, uncover vulnerabilities, and enhance the resilience of deployed AI models.
Upon completion of this training, participants will be capable of:
- Simulating real-world threats targeting machine learning models.
- Creating adversarial examples to evaluate model robustness.
- Assessing the attack surface of AI APIs and pipelines.
- Developing red teaming strategies for AI deployment environments.
Securing Edge AI and Embedded Intelligence
14 HoursThis instructor-led, live training in South Africa (online or onsite) is designed for intermediate-level engineers and security professionals who want to safeguard AI models deployed at the edge against threats like tampering, data leakage, adversarial inputs, and physical attacks.
By the end of this training, participants will be able to:
- Identify and assess security risks in edge AI deployments.
- Apply tamper resistance and encrypted inference techniques.
- Harden edge-deployed models and secure data pipelines.
- Implement threat mitigation strategies specific to embedded and constrained systems.
Securing AI Models: Threats, Attacks, and Defenses
14 HoursThis instructor-led, live training in South Africa (online or onsite) targets intermediate-level machine learning and cybersecurity professionals keen to understand and mitigate emerging threats against AI models, utilising both conceptual frameworks and hands-on defenses like robust training and differential privacy.
By the conclusion of this training, participants will be able to:
- Identify and classify AI-specific threats, including adversarial attacks, inversion, and poisoning.
- Utilise tools such as the Adversarial Robustness Toolbox (ART) to simulate attacks and test models.
- Implement practical defenses, including adversarial training, noise injection, and privacy-preserving techniques.
- Design threat-aware model evaluation strategies within production environments.
Security and Privacy in TinyML Applications
21 HoursTinyML involves the deployment of machine learning models onto low-power, resource-constrained devices operating at the edge of the network.
This instructor-led live training, available either online or onsite, is designed for advanced professionals seeking to secure TinyML pipelines and implement privacy-preserving techniques in edge AI applications.
Upon completing this course, participants will be able to:
- Identify security risks specific to on-device TinyML inference.
- Implement privacy-preserving mechanisms for edge AI deployments.
- Harden TinyML models and embedded systems against adversarial threats.
- Apply best practices for secure data handling in constrained environments.
Course Format
- Engaging lectures supported by expert-led discussions.
- Practical exercises emphasising real-world threat scenarios.
- Hands-on implementation using embedded security and TinyML tooling.
Course Customisation Options
- Organisations may request a tailored version of this training to align with their specific security and compliance needs.
Safe & Secure Agentic AI: Governance, Identity, and Red-Teaming
21 HoursThis programme explores the governance, identity management, and adversarial testing of agentic AI systems, with a strong emphasis on enterprise-safe deployment patterns and practical red-teaming methodologies.
This instructor-led, live training (available online or on-site) is tailored for advanced practitioners who aim to design, secure, and evaluate agent-based AI systems within production environments.
Upon completion of this training, participants will be equipped to:
- Establish governance models and policies to ensure safe agentic AI deployments.
- Design non-human identity and authentication flows for agents, ensuring least-privilege access.
- Implement access controls, audit trails, and observability mechanisms specifically tailored to autonomous agents.
- Plan and execute red-team exercises to identify misuses, escalation paths, and data exfiltration risks.
- Mitigate common threats to agentic systems through policy, engineering controls, and continuous monitoring.
Format of the Course
- Interactive lectures and threat-modeling workshops.
- Hands-on labs covering identity provisioning, policy enforcement, and adversary simulation.
- Red-team and blue-team exercises, concluding with a final assessment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
