Swift-Healer: Firmware-Reconfigurable Self-Healing for Remote Glitch-Injection on Autonomous Navigation Systems

Published

June 22, 2026

Author(s)

Kostas Amberiadis, Guru Prasadh Venkataramani, Ali Suvizi Suvizi, Joshua Iwu

Abstract

Autonomous Navigation Systems (ANS) incorporate many safety-critical functions, such as collision avoidance. Recent works have shown how remote clock/voltage glitch injections pose an imminent threat to mission-sensitive modules in the ADS domain: timing/power perturbations can cascade into severe accuracy loss and latency drift, especially in the perception stages. In this paper, we present Swift- Healer, a firmware-reconfigurable self-healing architecture that unifies prediction-detection modules and an automated healing unit to mitigate remote clock/voltage glitches, while satisfying latency constraints. Our solution leverages a chiplet-based architecture that offers isolation from compromised hardware modules, while enabling self-repair in the firmware management layer. Our proposed design incorporates an autonomous monitor that is a combination of glitch predictor and a reactive detector. We implement our design on a Zynq–7000 with a PL accelerator, where Swift-Healer predicts glitches two control cycles (real–time loop iterations; here ≈ 30 μs each) early (F1=0.87); if a prediction is below the confidence threshold, the reactive detector flags the fault, and deploys the healing module within 0.005–5.0 ms healing time. The system restores perception to ∼0.96 F1 at 0.03 ms latency, holds steady-state power at 1.95 W, and exhibits transient peaks up to ∼2.44 W.

Proceedings Title

GLSVLSI '26: Proceedings of the Great Lakes Symposium on VLSI 2026

Conference Dates

June 22-24, 2026

Conference Location

Canandaigua, NY, US

Conference Title

Great Lakes Symposium on VLSI (GLSVLSI) 2026

Pub Type

Conferences

Download Paper

https://doi.org/10.1145/3787109.3815273

Local Download

Keywords

autonomous navigation systems, self-healing firmware, remote glitch injection, chiplet architectures, Field Programmable Gate Arrays

Citation

Amberiadis, K. , Venkataramani, G. , Suvizi, A. and Iwu, J. (2026), Swift-Healer: Firmware-Reconfigurable Self-Healing for Remote Glitch-Injection on Autonomous Navigation Systems, GLSVLSI '26: Proceedings of the Great Lakes Symposium on VLSI 2026, Canandaigua, NY, US, [online], https://doi.org/10.1145/3787109.3815273, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=961103 (Accessed August 18, 2026)

Additional citation formats