Back to Search Start Over

Discrete Randomized Smoothing Meets Quantum Computing

Authors :
Wollschläger, Tom
Saxena, Aman
Franco, Nicola
Lorenz, Jeanette Miriam
Günnemann, Stephan
Source :
International Conference on Quantum Computing and Engineering, 2024
Publication Year :
2024

Abstract

Breakthroughs in machine learning (ML) and advances in quantum computing (QC) drive the interdisciplinary field of quantum machine learning to new levels. However, due to the susceptibility of ML models to adversarial attacks, practical use raises safety-critical concerns. Existing Randomized Smoothing (RS) certification methods for classical machine learning models are computationally intensive. In this paper, we propose the combination of QC and the concept of discrete randomized smoothing to speed up the stochastic certification of ML models for discrete data. We show how to encode all the perturbations of the input binary data in superposition and use Quantum Amplitude Estimation (QAE) to obtain a quadratic reduction in the number of calls to the model that are required compared to traditional randomized smoothing techniques. In addition, we propose a new binary threat model to allow for an extensive evaluation of our approach on images, graphs, and text.

Details

Database :
arXiv
Journal :
International Conference on Quantum Computing and Engineering, 2024
Publication Type :
Report
Accession number :
edsarx.2408.00895
Document Type :
Working Paper