Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LiteAtt: Secure and Seamless IoT Services Using TinyML-based Self-Attestation as a Primitive

Varun Kohli, Biplab Sikdar

Abstract

As the Internet of Things (IoT) becomes an integral part of critical infrastructure, smart cities, and consumer networks, there has been an increase in the number of software attacks on the microcontrollers (MCUs) that constitute such networks. Runtime firmware attestation, i.e., the verification of a firmware's integrity, has become instrumental, and prior work focuses on lightweight IoT MCUs, offloading the verification task to capable remote verifiers. However, modern IoT devices feature large flash and volatile memory, on-device TinyML inference, and Trusted Execution Environments (TEE). Leveraging these capabilities, this paper presents a verifier-less, hybrid Self-Attestation (SA) framework called LiteAtt, which is based on TinyML execution in the Arm TrustZone of an IoT MCU for quick, on-device evaluation of the IoT firmware's SRAM footprint. LiteAtt takes a step towards ubiquitous intelligence and decentralized trust in IoT networks. It eliminates the need for firmware copies for attestation, and protects the privacy of user SRAM data by leveraging twin devices to train the TinyML models. The proposed framework achieves an average accuracy of 98.7%, F1 score of 99.33%, TPR of 98.72%, and TNR of 97.45% on SRAM attestation datasets collected from real devices. LiteAtt operates with a latency of 1.29ms, an energy consumption of 42.79uJ, and a runtime memory overhead of up to 32KB, which is suitable for battery-operated Arm Cortex-M devices. A security analysis is provided for the protocol regarding mutual authentication, confidentiality, integrity, SRAM privacy, and defense against replay and impersonation attacks. Practical deployment scenarios and future works are also discussed.

LiteAtt: Secure and Seamless IoT Services Using TinyML-based Self-Attestation as a Primitive

Abstract

As the Internet of Things (IoT) becomes an integral part of critical infrastructure, smart cities, and consumer networks, there has been an increase in the number of software attacks on the microcontrollers (MCUs) that constitute such networks. Runtime firmware attestation, i.e., the verification of a firmware's integrity, has become instrumental, and prior work focuses on lightweight IoT MCUs, offloading the verification task to capable remote verifiers. However, modern IoT devices feature large flash and volatile memory, on-device TinyML inference, and Trusted Execution Environments (TEE). Leveraging these capabilities, this paper presents a verifier-less, hybrid Self-Attestation (SA) framework called LiteAtt, which is based on TinyML execution in the Arm TrustZone of an IoT MCU for quick, on-device evaluation of the IoT firmware's SRAM footprint. LiteAtt takes a step towards ubiquitous intelligence and decentralized trust in IoT networks. It eliminates the need for firmware copies for attestation, and protects the privacy of user SRAM data by leveraging twin devices to train the TinyML models. The proposed framework achieves an average accuracy of 98.7%, F1 score of 99.33%, TPR of 98.72%, and TNR of 97.45% on SRAM attestation datasets collected from real devices. LiteAtt operates with a latency of 1.29ms, an energy consumption of 42.79uJ, and a runtime memory overhead of up to 32KB, which is suitable for battery-operated Arm Cortex-M devices. A security analysis is provided for the protocol regarding mutual authentication, confidentiality, integrity, SRAM privacy, and defense against replay and impersonation attacks. Practical deployment scenarios and future works are also discussed.
Paper Structure (42 sections, 6 theorems, 13 figures, 7 tables, 1 algorithm)

This paper contains 42 sections, 6 theorems, 13 figures, 7 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Remote Attestation
  4. Self-Attestation
  5. Background
  6. Static Random Access Memory (SRAM)
  7. TinyML: AI on Tiny Devices
  8. Trusted Execution Environment
  9. Network and Threat Model
  10. Proposed Self-Attestation Framework
  11. Setup Phase
  12. Attestation Phase
  13. Experimental Setup
  14. Hardware and Software
  15. Hardware
  16. ...and 27 more sections

Key Result

Theorem 1

Under $(A_1, A_2, A_5)$, $\mathcal{A}$'s advantage to impersonate $\mathcal{P}_i$ to $\mathcal{P}_j$ or vice-versa is $Adv^{AUTH}_{LiteAtt}(\mathcal{A}) \leq negl(\lambda)$.

Figures (13)

  • Figure 1: Typical network model for remote firmware attestation. A central verifier remotely attests each prover in the network. LiteAtt moves away from this toward decentralized, self-attestation.
  • Figure 2: Logical sections of an SRAM.
  • Figure 3: Overview of the IoT network model for SA. Capable MCUs in the cluster furnish SA reports during the connection handshake to enhance trust.
  • Figure 4: Overview of the proposed LiteAtt attestation framework.
  • Figure 5: FSM for $\text{App}_{SA}(id_s,r_s,a_{self})$. Major states and their respective line numbers in Algorithm \ref{['algo:attest']} are VALIDATE_INPUT (lines 4-7), VALIDATE_SENDER (lines 8-17), SELF_ATTEST (lines 19-29), ABORT (lines 5,7,13,15,17) and SUCCESS (line 20, 29).
  • ...and 8 more figures

Theorems & Definitions (12)

  • Theorem 1
  • proof
  • Theorem 2
  • proof
  • Theorem 3
  • proof
  • Theorem 4
  • proof
  • Theorem 5
  • proof
  • ...and 2 more