Memory Offloading for Remote Attestation of Multi-Service IoT Devices

Remote attestation (RA) is an effective malware detection mechanism that allows a trusted entity (Verifier) to detect a potentially compromised remote device (Prover). The recent research works are proposing advanced Control-Flow Attestation (CFA) protocols that are able to trace the Prover's execution flow to detect runtime attacks. Nevertheless, several memory regions remain unattested, leaving the Prover vulnerable to data memory and mobile adversaries. Multi-service devices, whose integrity is also dependent on the integrity of any attached external peripheral devices, are particularly vulnerable to such attacks. This paper extends the state-of-the-art RA schemes by presenting ERAMO, a protocol that attests larger memory regions by adopting the memory offloading approach. We validate and evaluate ERAMO with a hardware proof-of-concept implementation using a TrustZone-capable LPC55S69 running two sensor nodes. We enhance the protocol by providing extensive memory analysis insights for multi-service devices, demonstrating that it is possible to analyze and attest the memory of the attached peripherals. Experiments confirm the feasibility and effectiveness of ERAMO in attesting dynamic memory regions.