Autonomous Navigation Systems (ANS) incorporate many safety-critical functions, such as collision avoidance. Recent studies have shown how remote clock/voltage glitch injections pose an imminent threat to mission-sensitive modules in the autonomous navigation domain: timing/power perturbations in the perception stages can cascade into severe accuracy loss, and latency drift for downstream tasks. 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 the application latency constraints. Our solution leverages a chiplet-based architecture that offers isolation from compromised hardware modules, while enabling self-healing in the firmware management layer. We implement our design on a Zynq–7000 with a hardware accelerator, where Swift-Healer predicts glitches within ANS kernels up to two real-time loop iterations earlier (≈ 0.06 ms), thereby giving abundant time for self-healing. When the prediction confidence is low, the reactive detector provides a fallback path for rapid fault detection.
Autonomous Navigation Systems (ANS) incorporate many safety-critical functions, such as collision avoidance. Recent studies have shown how remote clock/voltage glitch injections pose an imminent threat to mission-sensitive modules in the autonomous navigation domain: timing/power perturbations in...
See full abstract
Autonomous Navigation Systems (ANS) incorporate many safety-critical functions, such as collision avoidance. Recent studies have shown how remote clock/voltage glitch injections pose an imminent threat to mission-sensitive modules in the autonomous navigation domain: timing/power perturbations in the perception stages can cascade into severe accuracy loss, and latency drift for downstream tasks. 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 the application latency constraints. Our solution leverages a chiplet-based architecture that offers isolation from compromised hardware modules, while enabling self-healing in the firmware management layer. We implement our design on a Zynq–7000 with a hardware accelerator, where Swift-Healer predicts glitches within ANS kernels up to two real-time loop iterations earlier (≈ 0.06 ms), thereby giving abundant time for self-healing. When the prediction confidence is low, the reactive detector provides a fallback path for rapid fault detection.
Hide full abstract
