Discrete Randomized Smoothing Meets Quantum Computing
This work addresses safety-critical concerns in quantum machine learning for discrete data, offering a novel speed-up for certification, though it is incremental in applying quantum techniques to an existing method.
The paper tackles the problem of computationally intensive certification of machine learning models against adversarial attacks by combining quantum computing with discrete randomized smoothing, achieving a quadratic reduction in model calls compared to traditional methods.
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.