Kursplan

Introduction to Privacy-Preserving AI

  • Core principles of data privacy in mobile applications
  • Regulatory drivers for on-device AI
  • Benefits and limitations of local processing

Understanding Nano Banana for On-Device Privacy

  • Nano Banana model architecture
  • Security properties and local execution paths
  • Supported platforms and mobile integration patterns

Data Handling and Local Processing Techniques

  • Collecting and storing sensitive data securely on-device
  • Minimizing data exposure using local inference
  • Anonymization and pseudonymization strategies

Implementing Privacy-Preserving AI Features

  • Creating AI-driven features without transmitting user data
  • Designing healthcare-, finance-, or compliance-ready workflows
  • Ensuring data isolation across app components

Security Considerations for On-Device Models

  • Protecting models from extraction or tampering
  • Secure sandboxing and permission management
  • Threat modeling for mobile AI systems

Compliance and Regulatory Alignment

  • Understanding GDPR, HIPAA, and financial-sector implications
  • Documenting privacy-by-design approaches
  • Maintaining auditability without compromising user data

Testing and Validating Privacy Guarantees

  • Testing workflows for unintended data leakage
  • Evaluating accuracy vs privacy trade-offs
  • Continuous validation across app updates

Deployment and Maintenance of Privacy-Focused AI Apps

  • Managing on-device model updates
  • Monitoring performance and compliance over time
  • Future-proofing applications for evolving regulations

Summary and Next Steps

Krav

  • An understanding of mobile or application development
  • Experience with Python, Kotlin, or Swift
  • Basic familiarity with AI or machine learning concepts

Audience

  • Enterprise teams
  • Compliance officers
  • Developers building sensitive applications
 14 timer

Antall deltakere


Pris per deltaker

Referanser (1)

Kommende kurs

Relaterte kategorier