AI Security Training in Michigan

This instructor-led professional development session in Michigan (online or in-person) is designed for junior to mid-level IT specialists seeking to integrate AI TRiSM principles into their institutional operations.

Upon completion of this training, participants will be equipped to:

• Comprehend the fundamental concepts and strategic value of AI trust, risk, and security management.
• Recognize and effectively reduce risks inherent in AI deployments.
• Apply security best practices specifically tailored for AI environments.
• Demonstrate knowledge of regulatory compliance and ethical imperatives in AI.
• Formulate robust strategies for AI governance and operational oversight.

This instructor-led training in Michigan covers governance, identity management, and red-teaming for agentic AI systems. Advanced practitioners will design secure deployments for government, implement least-privilege access, and execute adversarial testing to mitigate real-world threats in production environments.

This instructor-led live training in Michigan (available online or onsite) targets intermediate-level AI and cybersecurity professionals seeking to mitigate security vulnerabilities specific to AI models and systems, with a focus on highly regulated sectors such as finance, data governance, and consulting for government applications.

Upon completion of this training, participants will be equipped to:

• Identify adversarial attack vectors targeting AI systems and apply defensive strategies.
• Apply model hardening techniques to safeguard machine learning pipelines.
• Maintain data security and integrity within machine learning models.
• Navigate regulatory compliance obligations associated with AI security for government and other public entities.

This instructor-led live training in Michigan (online or onsite) is directed at senior security experts and machine learning specialists who aim to emulate threats against AI systems, detect vulnerabilities, and strengthen the resilience of operational AI models.

Upon completion, participants will possess the ability to:

• Emulate realistic threat scenarios affecting machine learning architectures.
• Produce adversarial instances to validate model stability.
• Analyze the security posture of AI application programming interfaces and process pipelines.
• Construct red teaming strategies appropriate for AI deployment contexts.

TinyML is an approach to deploying machine learning models on low-power, resource-constrained devices operating at the network edge.

This instructor-led, live training (online or onsite) is aimed at advanced-level professionals who wish to secure TinyML pipelines and implement privacy-preserving techniques in edge AI applications.

At the conclusion of this course, participants will be able to:

• Identify security risks unique 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.

Format of the Course

• Engaging lectures supported by expert-led discussions.
• Practical exercises emphasizing real-world threat scenarios.
• Hands-on implementation using embedded security and TinyML tooling.

Course Customization Options

• Organizations may request a tailored version of this training to align with their specific security and compliance needs.

This instructor-led, live training session, offered either online or onsite at Michigan, is designed for mid-level engineering and security professionals. The program focuses on securing AI models deployed in edge environments against threats including device tampering, data leakage, adversarial inputs, and physical attacks.

Upon completion, participants will be equipped to:

• Identify and evaluate security vulnerabilities in edge AI implementations.
• Apply tamper-resistant mechanisms and encrypted inference methodologies.
• Strengthen the resilience of edge-deployed models and secure data processing pipelines.
• Execute threat mitigation strategies tailored for embedded and resource-constrained systems.

This instructor-led, live training in Michigan (online or onsite) is designed for advanced-level professionals seeking to implement and evaluate methodologies such as federated learning, secure multiparty computation, homomorphic encryption, and differential privacy within production machine learning pipelines.

Upon completion of this training, participants will be equipped to:

• Analyze and contrast critical privacy-preserving techniques in machine learning.
• Develop federated learning systems utilizing open-source frameworks.
• Implement differential privacy protocols for secure data sharing and model training.
• Leverage encryption and secure computation methods to safeguard model inputs and outputs.

The integration of Artificial Intelligence (AI) into public sector operations introduces distinct challenges regarding operational risk, governance integrity, and cybersecurity resilience for federal, state, and local agencies.

This live, instructor-led training session, available both online and onsite, is designed specifically for government IT and risk management professionals. It targets those with limited prior exposure to AI, providing the necessary skills to evaluate, monitor, and secure AI systems within the regulatory and accountability frameworks of the public sector.

Upon completion, participants will be equipped to:

• Interpret core risk concepts associated with AI systems, including bias, unpredictability, and model drift.
• Apply AI-specific governance and auditing standards, such as the NIST AI RMF and ISO/IEC 42001, to government contexts.
• Identify cybersecurity threats that target AI models and associated data pipelines.
• Develop cross-departmental risk management strategies and ensure policy alignment for the responsible deployment of AI.

Course Format

• Interactive instruction and discussion focused on public sector use cases relevant to government.
• Practical exercises in applying AI governance frameworks and mapping policies.
• Scenario-based threat modeling and risk evaluation activities.

Customization Options

• Interested parties may contact us to discuss options for tailoring this training to specific agency needs.

This instructor-led, live training in Michigan (available online or in-person) targets intermediate-level leaders responsible for overseeing AI systems in government and enterprise environments. The course focuses on responsible governance and security, ensuring alignment with emerging global frameworks such as the EU AI Act, GDPR, ISO/IEC 42001, and the U.S. Executive Order on AI.

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

• Evaluate the legal, ethical, and regulatory implications of AI adoption across organizational units.
• Apply major AI governance frameworks, including the EU AI Act, NIST AI Risk Management Framework, and ISO/IEC 42001.
• Establish comprehensive security, auditing, and oversight policies for AI deployments in government and enterprise contexts.
• Develop rigorous procurement and usage standards for both third-party and in-house AI systems.

This instructor-led, live training session in Michigan (available online or onsite) is tailored for intermediate to advanced AI developers, architects, and product managers. The objective is 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.

Upon completion of this training, participants will be able to:

• Comprehend the core vulnerabilities of LLM-based systems
• Apply secure design principles to LLM application architecture
• Leverage tools such as Guardrails AI and LangChain for validation, filtering, and safety measures
• Integrate techniques such as sandboxing, red teaming, and human-in-the-loop review into production-grade pipelines

This instructor-led, live training in Michigan (online or onsite) targets intermediate-level professionals in machine learning and cybersecurity. It is designed to assist these individuals in understanding and mitigating emerging threats against AI models for government, employing both conceptual frameworks and hands-on defenses such as robust training and differential privacy.

Upon completion, participants will possess the capability to:

• Identify and categorize AI-specific threats, including adversarial attacks, inversion, and poisoning.
• Utilize the Adversarial Robustness Toolbox (ART) to simulate attacks and validate model integrity.
• Implement practical defenses, such as adversarial training, noise injection, and privacy-preserving methods.
• Develop threat-aware evaluation strategies for models in production environments.

This instructor-led, live training in Michigan (online or onsite) is designed 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.

Upon completion of this training, participants will be equipped to:

• Comprehend the distinct security risks inherent in AI systems.
• Recognize specific threat vectors, including adversarial attacks, data poisoning, and model inversion.
• Implement foundational governance models such as the NIST AI Risk Management Framework.
• Align AI adoption with emerging standards, compliance guidelines, and ethical principles relevant to public sector operations.

Aligned with 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.

This course offers a practical framework for securing modern AI-powered applications, APIs, copilots, and autonomous agents. Participants examine the distinctions between AI security and traditional web security, explore specific threats such as prompt injection, RAG poisoning, and agent abuse, and learn to protect AI systems through layered defenses including WAFs, AI gateways, API security, and guardrails. Through hands-on labs and real-world scenarios, participants develop the skills to identify AI attack patterns, secure LLM-based applications, and deploy effective runtime defenses suitable for production and government environments.

This course instructs software developers on the secure, design-level construction of AI-powered applications. Participants learn to protect chatbots, copilots, RAG pipelines, and AI agents against AI-specific threats, including prompt injection, data poisoning, tool misuse, secret leakage, and insecure model output. The curriculum covers secure prompt design, RAG security, least-privilege access control, guardrail implementation, and red-team testing, enabling developers to build AI features that are secure, reliable, and resilient in production environments.

This live, instructor-led training session in Michigan (available online or onsite) is tailored for security engineers and compliance officers aiming to strengthen deployment security, manage model access, and oversee on-premise AI workloads for government operations.

This instructor-led, live training in Michigan (online or onsite) is designed for security and ML engineers who must identify, test for, and defend against attacks on ML models and LLM-powered applications.