Speakers
Description
This project focuses on identifying quantum hardware based on its unique "quantum
noise fingerprint" using machine learning. Each quantum computer exhibits a distinct
noise signature due to physical imperfections, and recognizing these patterns can aid in
hardware development, calibration, and security. We utilized basic machine learning
algorithms (SVM, KNN) to analyse noise characteristics and predict which IBM quantum
machine executed a given circuit.
Methodology and Observations
Data was gathered from IBM's Qiskit platform, including actual hardware runs (facilitated
by a CSIR educational license) and refreshed software simulations. An HPC cluster was
essential for processing and simulating the extensive datasets due to the computational
demands, allowing for efficient parallel data transformation. The SVM and KNN machine
learning models were then trained on this data, after feature engineering and parameter
tuning was completed. Initial findings showed high accuracy (over 96%) when models
were trained and tested on data within the same category (e.g., training on hardware data
and testing on hardware data). However, a significant drop in accuracy was observed
when attempting to identify machines across different data types (e.g., training on
software simulations and testing on actual hardware). Furthermore, we noted that IBM's
refreshed simulation noise models are not static and evolve over time
| Presenting Author | Rameez Abdool |
|---|---|
| Institute | University of the Witwatersrand |
