Discrete Randomized Smoothing Meets Quantum Computing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909277461938176 |
|---|---|
| author | Wollschläger, Tom Saxena, Aman Franco, Nicola Lorenz, Jeanette Miriam Günnemann, Stephan |
| author_facet | Wollschläger, Tom Saxena, Aman Franco, Nicola Lorenz, Jeanette Miriam Günnemann, Stephan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00895 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Discrete Randomized Smoothing Meets Quantum Computing Wollschläger, Tom Saxena, Aman Franco, Nicola Lorenz, Jeanette Miriam Günnemann, Stephan Machine Learning Quantum Physics 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. |
| title | Discrete Randomized Smoothing Meets Quantum Computing |
| topic | Machine Learning Quantum Physics |
| url | https://arxiv.org/abs/2408.00895 |