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
Foundations of Security in TinyML
- Security challenges in resource-limited ML systems
- Threat models for TinyML deployments
- Risk categories for embedded AI applications
Protecting Data Privacy in Edge AI
- Privacy implications of on-device data processing
- Strategies to minimize data exposure and transmission
- Methods for decentralized data management
Adversarial Threats to TinyML Models
- Evasion and poisoning attack vectors
- Input manipulation on embedded sensors
- Evaluating vulnerabilities in constrained contexts
Hardening Embedded ML Security
- Firmware and hardware defense layers
- Access control and secure boot processes
- Best practices for securing inference pipelines
Privacy-Focused TinyML Techniques
- Quantization and model design strategies for privacy
- Methods for on-data anonymization on-device
- Lightweight encryption and secure computation approaches
Secure Deployment and Lifecycle Management
- Secure provisioning of TinyML hardware
- Over-the-air (OTA) updates and patching protocols
- Edge-level monitoring and incident response
Testing and Validating Secure TinyML Systems
- Frameworks for security and privacy testing
- Simulating practical attack scenarios
- Validation and regulatory compliance considerations
Case Studies and Practical Scenarios
- Reviewing security lapses in edge AI ecosystems
- Architecting resilient TinyML systems
- Balancing performance with security protections
Conclusions and Future Directions
Requirements
- Familiarity with embedded system architectures
- Practical experience with machine learning workflows
- Foundational knowledge of cybersecurity principles
Intended Audience
- Security analysts
- AI developers
- Embedded engineers
Testimonials (1)
The exercises
