Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 21 hours
Course Outline
Introduction to Security in TinyML
- Security challenges facing resource-constrained ML systems
- Threat models applicable to TinyML deployments
- Risk categories specific to embedded AI applications
Data Privacy in Edge AI
- Privacy implications of on-device data processing
- Strategies for reducing data exposure and transfer
- Methods for decentralized data management
Adversarial Attacks on TinyML Models
- Threats related to model evasion and poisoning
- Input manipulation via embedded sensors
- Evaluating vulnerabilities within constrained environments
Security Hardening for Embedded ML
- Protection layers for firmware and hardware
- Access control and secure boot mechanisms
- Best practices for securing inference pipelines
Privacy-Preserving TinyML Techniques
- Quantization and model design with privacy in mind
- On-device anonymization techniques
- Lightweight encryption and secure computation approaches
Secure Deployment and Maintenance
- Secure provisioning of TinyML devices
- OTA update and patching strategies
- Edge-level monitoring and incident response
Testing and Validation of Secure TinyML Systems
- Frameworks for security and privacy testing
- Simulation of real-world attack scenarios
- Considerations for validation and compliance
Case Studies and Applied Scenarios
- Examining security failures in edge AI ecosystems
- Designing resilient TinyML architectures
- Assessing the balance between performance and protection
Summary and Next Steps
Requirements
- A solid understanding of embedded system architectures
- Proficiency with machine learning workflows
- Familiarity with cybersecurity fundamentals
Audience
- Security analysts
- AI developers
- Embedded engineers
Testimonials (1)
The exercises
