Red Teaming AI Systems: Offensive Security for ML Models Training Course

This instructor-led live training, conducted in Latvia (online or on-site), targets intermediate-level enterprise leaders. It focuses on understanding how to govern and secure AI systems responsibly while maintaining compliance with emerging global frameworks, including the EU AI Act, GDPR, ISO/IEC 42001, and the U.S. Executive Order on AI.

By the end of the session, participants will be able to:

• Comprehend the legal, ethical, and regulatory risks of utilizing AI across organizational departments.
• Apply major AI governance frameworks, such as the EU AI Act, NIST AI RMF, and ISO/IEC 42001.
• Implement security, auditing, and oversight policies for enterprise AI deployment.
• Create procurement and usage guidelines for third-party and in-house AI solutions.

This course offers a practical introduction to securing modern AI-powered applications, APIs, copilots, and autonomous agents. Participants will learn how AI security diverges from traditional web security, examine 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 scenarios, students will acquire the skills to identify AI attack patterns, secure LLM-based applications, and deploy effective runtime defenses for production environments.

This instructor-led, live training session held in Latvia (either online or onsite) caters to IT professionals with beginner to intermediate expertise who aim to understand and integrate AI TRiSM within their organizations.

By the conclusion of the program, participants will gain the ability to:

• Understand the fundamental principles and critical role of AI trust, risk, and security management.
• Detect and reduce risks specific to AI environments.
• Adopt established security best practices for AI deployment.
• Interpret regulatory compliance obligations and ethical implications in AI.
• Create effective strategies for overseeing AI governance and management.

This instructor-led live training in Latvia (online or on-site) is designed for intermediate to advanced AI developers, architects, and product managers seeking to identify and mitigate risks in LLM-powered applications, including prompt injection, data leakage, and unfiltered outputs, while integrating security controls such as input validation, human-in-the-loop oversight, and output guardrails.

By the end of the 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.

This course instructs software developers on building AI-powered applications with inherent security. Participants learn to safeguard chatbots, copilots, RAG pipelines, and AI agents against specific threats including prompt injection, data poisoning, tool abuse, secret leakage, and insecure model outputs. The curriculum addresses secure prompt design, RAG security, least-privilege access, guardrails, and red-team testing, enabling developers to create AI features that are secure, reliable, and resilient in production environments.

This live, instructor-led session—delivered online or on-site—is designed for intermediate-level AI and cybersecurity experts aiming to tackle the specific security weaknesses in AI models and systems. It is especially beneficial for those working in highly regulated fields such as finance, data governance, and consulting.

By the conclusion of this training, participants will be able to:

• Recognize adversarial attacks on AI systems and implement corresponding defenses.
• Deploy model hardening techniques to protect machine learning pipelines.
• Ensure robust data security and integrity in machine learning models.
• Navigate regulatory compliance mandates related to AI security.

This instructor-led, live session in Latvia (online or onsite) is targeted at security engineers and compliance officers aiming to fortify EXO deployments, manage model access, and supervise AI workloads operating exclusively on-premise.

This live, instructor-led training in Latvia (online or onsite) is tailored for beginner-level IT security, risk, and compliance professionals aiming to understand core AI security concepts, threat vectors, and global frameworks like the NIST AI RMF and ISO/IEC 42001.

By the conclusion of this training, participants will be capable of:

• Understanding the unique security risks associated with AI systems.
• Identifying threat vectors, including adversarial attacks, data poisoning, and model inversion.
• Applying foundational governance models such as the NIST AI Risk Management Framework.
• Ensuring AI use aligns with emerging standards, compliance guidelines, and ethical principles.

This live, instructor-led training in Latvia (available online or onsite) is designed for security and ML engineers who need to identify, test, and defend against attacks targeting ML models and LLM-powered applications.

Grounded in the latest OWASP GenAI Security Project guidelines, this session enables participants to learn how to detect, evaluate, and counteract AI-specific threats through hands-on exercises and realistic scenarios.

This live, instructor-led training in Latvia, offered online or onsite, is tailored for advanced professionals aiming to deploy and assess key privacy-enhancing techniques. Participants will explore federated learning, secure multiparty computation, homomorphic encryption, and differential privacy within real-world machine learning pipelines.

Upon completion, learners will be equipped to:

• Evaluate and distinguish between critical privacy-preserving methodologies in machine learning.
• Deploy federated learning architectures leveraging established open-source frameworks.
• Integrate differential privacy to ensure secure data exchange and robust model training.
• Utilize encryption and secure computation protocols to shield model inputs and outputs.

This instructor-led live training, delivered in Latvia (either online or on-site), is designed for intermediate-level engineers and security professionals aiming to secure edge-deployed AI models against threats such as tampering, data leakage, adversarial inputs, and physical attacks.

By the conclusion of this training, participants will be capable of:

• Identifying and evaluating security risks in edge AI deployments.
• Applying tamper resistance and encrypted inference techniques.
• Hardening edge-deployed models and securing data pipelines.
• Implementing threat mitigation strategies specific to embedded and constrained systems.

This instructor-led live training in Latvia, conducted online or onsite, is tailored for intermediate machine learning and cybersecurity professionals. It focuses on understanding and mitigating emerging threats to AI models through both theoretical frameworks and practical defenses like robust training and differential privacy.

By the end of the training, participants will be able to:

• Identify and classify AI-specific threats, such as adversarial attacks, inversion, and poisoning.
• Utilize tools like the Adversarial Robustness Toolbox (ART) to simulate attacks and test models.
• Apply practical defenses, including adversarial training, noise injection, and privacy-preserving techniques.
• Design threat-aware model evaluation strategies for production environments.