Get in Touch
 Duration 14 hours

Course Outline

Foundations of Privacy-Preserving ML

  • Understanding risks and driving factors in sensitive data contexts
  • Survey of privacy-preserving ML methodologies
  • Threat modeling and regulatory frameworks (e.g., GDPR, HIPAA)

Federated Learning

  • Core concepts and system architecture of federated learning
  • Mechanisms for client-server synchronization and data aggregation
  • Practical implementation using PySyft and Flower

Differential Privacy

  • Theoretical underpinnings and mathematical foundations of differential privacy
  • Integration of DP in data querying and model training processes
  • Application of Opacus and TensorFlow Privacy libraries

Secure Multiparty Computation (SMPC)

  • Exploration of SMPC protocols and practical use cases
  • Comparison of encryption-based methods versus secret-sharing techniques
  • Building secure computation workflows with CrypTen or PySyft

Homomorphic Encryption

  • Distinguishing between fully and partially homomorphic encryption
  • Performing encrypted inference for confidential workloads
  • Hands-on experimentation with TenSEAL and Microsoft SEAL

Industry Applications and Case Studies

  • Healthcare sector: Applying federated learning to medical AI
  • Financial sector: Secure collaboration for risk modeling and compliance
  • Defense and government-specific privacy scenarios

Requirements

  • A solid grasp of fundamental machine learning principles
  • Proficiency in Python and major ML libraries (e.g., PyTorch, TensorFlow)
  • Background knowledge in data privacy or cybersecurity is advantageous

Target Audience

  • AI researchers and developers
  • Professionals in data protection and privacy compliance
  • Security engineers operating in highly regulated sectors

Need help picking the right course?
taiwan@nobleprog.com or +65 88708290

Testimonials (3)

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

Upcoming Courses

Privacy-Preserving Machine Learning

2026-12-31 09:30
14 hours
Taipei, Aurora

Privacy-Preserving Machine Learning

2027-01-14 09:30
14 hours
Taipei- Concord

Privacy-Preserving Machine Learning

2027-01-28 09:30
14 hours
Taipei Walsin Xinyi

Privacy-Preserving Machine Learning

2027-02-11 09:30
14 hours
Taichung, Global

Related Courses

ISACA Advanced in AI Security Management (AAISM)

 21 Hours
This advanced ISACA course in Taiwan empowers professionals to effectively govern and protect AI systems. It addresses risk assessment, secure architecture, and compliance, enabling leaders to harmonize AI security with organizational goals while bolstering operational resilience.
Read more...

AI Governance, Compliance, and Security for Enterprise Leaders

 14 Hours

This instructor-led, live training in Taiwan (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 completion of this training, participants will be able to:

  • Comprehend 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 policies for security, auditing, and oversight regarding AI deployment within the enterprise.
  • Develop guidelines for procurement and usage of both third-party and in-house AI systems.
Read more...

AI Risk Management and Security in the Public Sector

 7 Hours
This instructor-led training on Taiwan equips public sector IT professionals with the skills to manage AI risk and security. Participants will utilize frameworks such as the NIST AI RMF, mitigate cybersecurity threats, and establish robust governance plans for secure AI integration.
Read more...

Practical AI Security for Security Teams

 35 Hours

This instructor-led live training in Taiwan (online or onsite) is designed for security engineers, SOC analysts, and platform teams seeking to defend AI applications, APIs, copilots, and autonomous agents using WAFs, AI gateways, guardrails, detection engineering, and layered runtime defenses.

Read more...

Introduction to AI Trust, Risk, and Security Management (AI TRiSM)

 21 Hours

This instructor-led, live training in Taiwan (online or onsite) is aimed at beginner-level to intermediate-level IT professionals who wish to understand and implement AI TRiSM in their organizations.

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

  • Grasp the key concepts and importance of AI trust, risk, and security management.
  • Identify and mitigate risks associated with AI systems.
  • Implement security best practices for AI.
  • Understand regulatory compliance and ethical considerations for AI.
  • Develop strategies for effective AI governance and management.
Read more...

Building Secure and Responsible LLM Applications

 14 Hours

This instructor-led, live training in Taiwan (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.
Read more...

Building Secure AI Applications

 21 Hours

This instructor-led live training in Taiwan, available online or onsite, is designed for developers and platform engineers who want to build AI features that resist prompt injection, data poisoning, tool abuse, and secret leakage—ensuring security by design rather than remediation after the fact.

Read more...

Cybersecurity for AI and Agentic Systems

 21 Hours

This live, instructor-led training in Taiwan (online or onsite) is designed for technical managers, architects, and security engineers who aim to secure generative AI and agentic systems throughout the delivery process. The curriculum covers threat modeling, guardrails, agent permissions, pipeline security, and governance.

Read more...

Cybersecurity in AI Systems

 14 Hours

This instructor-led, live training in Taiwan (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.
Read more...

EXO Security and Governance: Offline Model Management

 14 Hours

This instructor-led, live training in Taiwan (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.

Read more...

Introduction to AI Security and Risk Management

 14 Hours

This instructor-led, live training in Taiwan (online or on-site) is designed for beginner-level IT security, risk, and compliance professionals who want to grasp 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:

  • Comprehend the unique security risks posed 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 usage with emerging standards, compliance guidelines, and ethical principles.
Read more...

ML Security and AI Red Teaming

 14 Hours

This instructor-led, live training in Taiwan (online or onsite) is aimed at security and ML engineers who need to identify, test, and defend against attacks on ML models and LLM-powered applications.

Read more...

OWASP GenAI Security

 14 Hours

Aligned with the latest OWASP GenAI Security Project guidance, this training enables participants to identify, evaluate, and mitigate AI-specific threats through hands-on exercises and real-world scenarios.

Read more...

Red Teaming AI Systems: Offensive Security for ML Models

 14 Hours

This instructor-led, live training in Taiwan (online or onsite) is aimed at advanced-level security professionals and ML specialists who wish to simulate attacks on AI systems, uncover vulnerabilities, and enhance the robustness of deployed AI models.

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

  • Simulate real-world threats to machine learning models.
  • Generate adversarial examples to test model robustness.
  • Assess the attack surface of AI APIs and pipelines.
  • Design red teaming strategies for AI deployment environments.
Read more...

Securing Edge AI and Embedded Intelligence

 14 Hours

This instructor-led, live training in Taiwan (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.

Upon completing this training, participants will be able to:

  • Identify and evaluate security risks associated with edge AI deployments.
  • Apply tamper-resistant measures and encrypted inference techniques.
  • Harden edge-deployed models and secure data pipelines.
  • Implement threat mitigation strategies tailored to embedded and constrained systems.
Read more...

Related Categories

AI Security
AI Security