Locking down the Edge: How NVIDIA and OEMs Use TPM 2.0 to Secure Physical AI. Meeting EU CRA requirements using TPM 2.0
Edge and Physical AI systems must guarantee the secure and safe execution of compute tasks. To solve this, NVIDIA builds Trusted Platform Modules (TPM 2.0) directly into its enterprise-ready platform for physical AI, the IGX Thor. The commercial ecosystem has fully adopted this hardware-backed approach. Lenovo and Wincomm released new ruggedized, industrial edge AI computers featuring discrete TPM 2.0 solutions to ensure regulatory compliance and data security. This talk provides concrete details how TPM 2.0 protects Physical AI while remaining accessible. We detail advanced security guarantees beyond basic key storage, covering authenticated bus communications and hardware tamper defenses. Finally, we map these hardware capabilities directly to EU Cyber Resilience Act (CRA) compliance.
Key Takeaways:
- Mapping Edge AI security needs to TPM 2.0 capabilities.
- Advanced TPM 2.0 security capabilities matching Physical AI needs.
- Mitigating physical tampering and bus-level attacks on Edge hardware.
- Meeting EU CRA requirements using TPM 2.0.
20-minute talk with demo "Secure GPIO for Physical AI using TPM 2.0".
Copyright 2026 Dimi Tomov (CEO of EnactTrust & Founder of TPM.dev)
With over 20 years of experience in the field, Dimi is focused on securing the new generation of intelligent and connected devices. Dimi is CEO of EnactTrust, chair of the IoT Workgroup at the Trusted Computing Group (TCG), author of the public TPM 2.0 training courses available on OpenSecurityTraining2, and runs the TPM.dev developer community with of over 1,000 members.
Dimi’s background is industrial automation, and over the years he has helped build the fastest Hearing Aid Detection Algorithm for Sivantos (ex Siemens Hearing aids), helped Spotify create the CarThing IoT product, and various other smart and connected systems sold from Australia to USA.
Dimi entered the Edge AI industry as the Senior Embedded Engineer at Edge Impulse, the end-to-end development platform for training and deploying machine learning models on edge and microcontroller devices.