• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Discrete Randomized Smoothing Meets Quantum Computing
 
  • Details
  • Full
Options
2024
Conference Paper
Title

Discrete Randomized Smoothing Meets Quantum Computing

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.
Author(s)
Wollschläger, Tom
Technische Universität München  
Saxena, Aman
Technische Universität München  
Franco, Nicola  
Fraunhofer-Institut für Kognitive Systeme IKS  
Lorenz, Jeanette Miriam  orcid-logo
Fraunhofer-Institut für Kognitive Systeme IKS  
Günnemann, Stephan
Technische Universität München  
Mainwork
IEEE Quantum Week 2024. Proceedings. Volume III: Third IEEE Quantum Science and Engineering Education Conference, QSEEC 2024  
Project(s)
BayQS
Funder
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie  
Conference
Quantum Science and Engineering Education Conference 2024  
Quantum Week 2024  
Open Access
DOI
10.1109/QCE60285.2024.00180
Language
English
Fraunhofer-Institut für Kognitive Systeme IKS  
Fraunhofer Group
Fraunhofer-Verbund IUK-Technologie  
Keyword(s)
  • quantum machine learning

  • QML

  • certifiable robustness

  • randomized smoothing

  • quantum amplitude estimation

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024