Power Side-Channel Membership Inference Attack on Embedded Machine Learning

Name: Power Side-Channel Membership Inference Attack on Embedded Machine Learning
Uploaded: 2026-10-11T16:43:13.478697+00:00
Duration: 904 s
Description: PSCMIA is a power side-channel attack that infers whether a specific data sample was used to train an embedded ML model, even without access to prediction outputs. The method profiles shadow models and uses trace analysis to detect membership leakage in the physical power consumption of devices like STM32F3.

PSCMIA is a power side-channel attack that infers whether a specific data sample was used to train an embedded ML model, even without access to prediction outputs. The method profiles shadow models and uses trace analysis to detect membership leakage in the physical power consumption of devices like STM32F3.

Open the full episode