Shield your AI systems from emerging threats through practical, instructor-led training in AI Security.
These live sessions equip learners to safeguard machine learning models, mitigate adversarial attacks, and establish trustworthy, resilient AI systems.
Training is available via online live classes using a remote desktop connection, or through onsite live training in Southampton, incorporating interactive exercises and real-world case studies.
Onsite live training can be conducted at your premises in Southampton or at a NobleProg corporate training centre in Southampton.
Also referred to as Secure AI, ML Security, or Adversarial Machine Learning.
NobleProg – Your Local Training Provider
Southampton
International House, Southampton International Business Park, Southampton, united kingdom, SO18 2RZ
This centre occupies a great position - highly visible from the M27 motorway. The building's focal point is a beautiful atrium flooding the reception area with natural light. A comfortable, professional business lounge and a large breakout area where you can relax or network add to the welcoming atmosphere. This is an outstanding south coast location next to Southampton airport with air, road and rail transport links on the doorstep. Regular launches and exhibitions held at the centre have contributed to its reputation as a hub of business and cultural activity. Southampton is an innovative and enterprising city with thousands of thriving organisations and tens of thousands of productive people. The most significant sectors in terms of businesses and employee numbers are distribution, tourism, banking and finance-related activities. It also has one of the top 10 research-led universities in the UK, which provides a wide range of services to the business community.
This advanced ISACA course in Southampton empowers professionals to govern and secure AI systems. It addresses risk assessment, secure design, and compliance, enabling leaders to align AI security with organisational goals and effectively enhance operational resilience.
This live, instructor-led training in Southampton (available online or on-site) is tailored for IT professionals with beginner to intermediate experience who seek to understand and implement AI TRiSM within their organisations.
By the conclusion of this programme, participants will be capable of:
Grasping the core concepts and the vital importance of AI trust, risk, and security management.
Identifying and mitigating risks linked to AI systems.
Implementing security best practices for AI.
Understanding regulatory compliance and ethical considerations for AI.
Developing strategies for effective AI governance and management.
This instructor-led training in Southampton addresses governance, identity management, and red-teaming for agentic AI systems. Advanced practitioners will learn to design secure deployments, implement least-privilege access, and conduct adversarial testing to mitigate real-world threats in production environments.
This instructor-led, live training in Southampton (online or on-site) is designed for intermediate-level AI and cybersecurity professionals seeking to comprehend and mitigate the specific security vulnerabilities inherent in AI models and systems, particularly within highly regulated sectors such as finance, data governance, and consulting.
Upon completing this training, participants will be equipped to:
Comprehend the various adversarial attacks targeting AI systems and the defensive strategies employed against them.
Apply model hardening techniques to fortify machine learning pipelines.
Safeguard data security and integrity within machine learning models.
Navigate the regulatory compliance landscape concerning AI security.
This instructor-led live training, conducted in Southampton (either online or onsite), is tailored for advanced security experts and ML specialists seeking to simulate attacks on AI systems, identify vulnerabilities, and bolster the robustness of live AI models.
By the conclusion of this session, participants will be capable of:
Simulating real-world threats aimed at machine learning models.
Generating adversarial examples to probe model resilience.
Assessing the attack surface of AI APIs and pipelines.
Designing red teaming strategies specific to AI deployment environments.
This live, instructor-led training in Southampton empowers senior professionals to secure TinyML pipelines on edge devices. It covers implementing privacy-preserving techniques, strengthening models against adversarial attacks, and applying best practices for secure data handling in constrained environments.
Targeted at intermediate-level engineers and security professionals, this instructor-led live training in Southampton (online or onsite) is dedicated to securing edge-deployed AI models against threats such as tampering, data leakage, adversarial inputs, and physical attacks.
By the end of the programme, 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.
This instructor-led, live training in Southampton (online or onsite) targets advanced professionals aiming to implement and evaluate techniques including federated learning, secure multiparty computation, homomorphic encryption, and differential privacy in real-world machine learning pipelines.
By the end of the 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.
This instructor-led training in Southampton is designed for public sector IT professionals to master AI risk management and security. Participants will apply frameworks like NIST AI RMF, address cybersecurity threats, and build robust governance plans for secure AI deployment.
This instructor-led, live training in Southampton (online or onsite) is tailored for intermediate-level enterprise leaders aiming to understand the responsible governance and security of AI systems, 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, participants will be capable of:
Understanding the legal, ethical, and regulatory risks of AI utilisation across departments.
Interpreting and applying major AI governance frameworks (EU AI Act, NIST AI RMF, ISO/IEC 42001).
Establishing security, auditing, and oversight policies for enterprise AI deployment.
Developing procurement and usage guidelines for third-party and internal AI systems.
This instructor-led live training in Southampton (available online or onsite) is tailored for intermediate to advanced AI developers, architects, and product managers seeking to identify and mitigate risks associated with LLM-powered applications, including prompt injection, data leakage, and unfiltered output, while integrating security controls such as 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.
Delivered by an expert instructor, this live training in Southampton (available online or onsite) is designed for mid-level machine learning and cybersecurity specialists. It focuses on comprehending and neutralising contemporary threats to AI models, combining theoretical frameworks with practical mitigation strategies such as robust training and differential privacy.
Upon completion of this programme, attendees will be equipped to:
Recognise and categorise AI-specific risks, including adversarial attacks, inversion, and poisoning.
Utilise tools such as the Adversarial Robustness Toolbox (ART) to simulate attacks and evaluate model resilience.
Implement practical defences, such as adversarial training, noise injection, and privacy-preserving techniques.
Develop threat-aware evaluation strategies for models deployed in production environments.
This instructor-led, live training in Southampton (delivered online or onsite) is tailored for entry-level IT security, risk, and compliance professionals seeking to master foundational AI security concepts, threat vectors, and global frameworks such as the NIST AI RMF and ISO/IEC 42001.
By the end of the training, participants will be capable of:
Understanding the unique security risks posed by AI systems.
Identifying threat vectors such as adversarial attacks, data poisoning, and model inversion.
Applying foundational governance models like the NIST AI Risk Management Framework.
Aligning AI usage with emerging standards, compliance guidelines, and ethical principles.
Based on the latest OWASP GenAI Security Project guidance, participants will learn to identify, assess, and mitigate AI-specific threats through practical exercises and real-world scenarios.
This practical two-day programme is designed for engineers who are already familiar with the fundamentals of LLM security and are now ready to construct, test, and defend agentic AI systems within a government context. The course combines an in-depth analysis of the OWASP Top 10 for Agentic Applications (2026) with hands-on AI red-teaming, RAG security, MCP (Model Context Protocol) server security, and secure architecture patterns for multi-step, tool-using AI workflows.
It is tailored for engineering teams at i.AI, digital service teams, and departmental platform teams that are transitioning from simple chatbots to autonomous and semi-autonomous AI systems.
By the conclusion of the second day, delegates will have conducted live red-teaming exercises, built a defensive architecture for an agentic workflow, and received a department-ready playbook.
This instructor-led, live training in Southampton, delivered online or on-site, targets security engineers, SOC analysts, and platform teams. It focuses on defending AI applications, APIs, copilots, and autonomous agents using WAFs, AI gateways, guardrails, detection engineering, and layered runtime defences.
This practical one-day course equips software engineers, platform developers, and technical leads with a working foundation in AI-specific security threats and mitigations. The primary focus is on the OWASP Top 10 for Large Language Model Applications (2025) and the daily security considerations developers must address when building AI-powered government services.
The course is designed as an accessible entry point for engineering teams working across i.AI, digital services, and departmental engineering functions who are currently integrating LLMs and AI features into their codebases.
By the end of the day, participants will leave with a shared security baseline, a practical threat model for their own AI features, and a prioritised list of quick wins they can implement in the week following the training.
This instructor-led, live training in Southampton (online or on-site) targets developers and platform engineers seeking to build AI features that withstand prompt injection, data poisoning, tool abuse, and secret leakage. The emphasis is on security by design, ensuring protection is inherent rather than a post-incident patch.
This instructor-led, live training in Southampton, available online or on-site, is aimed at technical managers, architects, and security engineers who wish to secure generative AI and agentic systems in delivery, covering threat modelling, guardrails, agent permissions, pipeline security, and governance.
This instructor-led, live training on Southampton (delivered online or onsite) is designed for security engineers and compliance officers looking to fortify EXO deployments, manage model access, and govern AI workloads operating entirely on-premise.
This instructor-led, live training in Southampton (online or onsite) is designed for security and ML engineers who need to identify, test, and defend against attacks on ML models and LLM-powered applications.
Read more...
Last Updated:
Testimonials (4)
The exercises
Gianluca Bovo - Urmet
Course - Security and Privacy in TinyML Applications
inventory and identifying the different risk exposures within AI
Gary Cook - Cybersecurity and Information Technology Risk Division
Course - Introduction to AI Trust, Risk, and Security Management (AI TRiSM)
I really enjoyed learning about AI attacks and the tools out there to begin practicing and actively using for security testing. I took a lot of knowledge away which I didn't have at the beginning and the course met what I hoped it would be. My favorite part shown from the training was Comet Browser and was amazed at what it could do. Definitely something will be looking into more. Overall it was a great course and enjoyed learning all OWASP GenAI Top 10.
Patrick Collins - Optum
Course - OWASP GenAI Security
The profesional knolage and the way how he presented it before us
Miroslav Nachev - PUBLIC COURSE
Course - Cybersecurity in AI Systems
Provisional Upcoming Courses (Contact Us For More Information)
Online AI Security training in Southampton, AI Security training courses in Southampton, Weekend AI Security courses in Southampton, Evening Secure AI training in Southampton, AI Security instructor-led in Southampton, AI Security on-site in Southampton, Weekend AI Security training in Southampton, Secure AI trainer in Southampton, Secure AI boot camp in Southampton, Secure AI instructor-led in Southampton, Secure AI classes in Southampton, Online Secure AI training in Southampton, AI Security instructor in Southampton, Secure AI one on one training in Southampton, AI Security private courses in Southampton, Evening AI Security courses in Southampton, Secure AI coaching in Southampton