System protection on risc-v chips improves with bounded dynamic delegation
Reconfiguring System-Level Protection Through Bounded Delegation in RISC-V MCUs
Cryptography and SecurityHardware Architecture
Summary
Many small computing devices need to update their security settings while running, but current methods usually rely on fixed rules and let authorized parts make any changes they want. The authors found this can cause security problems if those parts set overly broad permissions. To fix this, they created a way to limit how much anyone can change protection rules, making sure updates stay within safe boundaries. They built and tested this system on a RISC-V chip and showed it works without slowing down the device or making it less reliable.
What this means in practice
- •For embedded system engineers: Enable secure on-the-fly adjustment of access controls in embedded devices running RISC-V MCUs to maintain protection boundaries during updates.
- •For iot device developers: Reduce downtime and improve security during over-the-air firmware updates by directly reconfiguring access policies under delegated authority.
Authors
Luís Cunha, José Martins, Manuel Rodríguez, Tiago Gomes, Uwe Moslehner, Kai Dieffenbach, Georg Schmalz, Kajetan Nuernberger, Thomas Roecker, Sandro Pinto
Abstract
MCU-based embedded and cyber-physical systems increasingly require protection policies to change at runtime as resources, software, and system composition evolve. Yet widely used COTS MCU protection mechanisms are still largely designed around statically established policies. While they can restrict which domains modify protection primitives, they generally do not constrain what policy an authorized domain may create. As a result, domains may expand protection rules beyond their intended scope or interfere with boundaries established by other domains. We identify bounded configuration authority as a missing primitive for secure dynamic policy evolution and introduce an ownership-aware model in which explicit ownership and rule containment bound both configuration authority and recursive delegation. Changes to active protection-rule ranges are validated before commit, preserving protection boundaries without extending the normal access-checking datapath. We implement the model in an open-source RISC-V World Checker integrated into a CVA6-based SoC. Our FPGA evaluation shows no degradation in access latency or operating frequency, with 7.1% LUT and 1.2% FF overhead for eight rules. In an OTA update case study, direct reconfiguration under delegated authority reduces policy-transition latency by 89.5% over hypervisor mediation and 94.6% over trusted firmware mediation, while preserving established authority boundaries. All artifacts will be open-sourced to support the evolution of RISC-V specifications and system-level protection designs.