mlsanityData to 7 Oct 2026

Differential Privacy Amplification in Quantum and Quantum-inspired Algorithms

arXiv 2203.03604 ↗First posted 7 Mar 2022quant-ph cs.CR cs.DScited by 6

Not on the map. Why?

Abstract (arXiv)

Differential privacy provides a theoretical framework for processing a dataset about n users, in a way that the output reveals a minimal information about any single user. Such notion of privacy is usually ensured by noise-adding mechanisms and amplified by several processes, including subsampling, shuffling, iteration, mixing and diffusion. In this work, we provide privacy amplification bounds for quantum and quantum-inspired algorithms. In particular, we show for the first time, that algorithms running on quantum encoding of a classical dataset or the outcomes of quantum-inspired classical sampling, amplify differential privacy. Moreover, we prove that a quantum version of differential privacy is amplified by the composition of quantum channels, provided that they satisfy some mixing conditions.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 25 of its 53 references that are in the map. First posted on arXiv 7 Mar 2022.

Builds on

25 of 53 references.

References · 25

  1. 2016Deep Learning with Differential Privacycited by 2,682
  2. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  3. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  4. 2020The effect of data encoding on the expressive power of variational quantum machine learning modelscited by 328
  5. 2013The Composition Theorem for Differential Privacycited by 290
  6. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
  7. 2021Supervised quantum machine learning models are kernel methodscited by 199
  8. 2018Distributed Differential Privacy via Shufflingcited by 115
  9. 2018Privacy Amplification by Iterationcited by 97
  10. 2020Robust data encodings for quantum classifierscited by 91
  11. 2021Encoding-dependent generalization bounds for parametrized quantum circuitscited by 81
  12. 2018A quantum-inspired classical algorithm for recommendation systemscited by 70
13 more
  1. 2016Quantum Recommendation Systemscited by 69
  2. 2020Quantum noise protects quantum classifiers against adversariescited by 68
  3. 2020An Equivalence Between Private Classification and Online Predictioncited by 63
  4. 2018q-means: A quantum algorithm for unsupervised machine learningcited by 55
  5. 2019Sampling-based sublinear low-rank matrix arithmetic framework for dequantizing quantum machine learningcited by 37
  6. 2018Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptionscited by 34
  7. 2022Quantum Differential Privacy: An Information Theory Perspectivecited by 32
  8. 2019Privacy Amplification by Mixing and Diffusion Mechanismscited by 21
  9. 2020Quantum statistical query learningcited by 19
  10. 2018Quantum-inspired low-rank stochastic regression with logarithmic dependence on the dimensioncited by 18
  11. 2015Learning with Differential Privacy: Stability, Learnability and the Sufficiency and Necessity of ERM Principlecited by 16
  12. 2018Quantum-inspired sublinear classical algorithms for solving low-rank linear systemscited by 11
  13. 2021Private learning implies quantum stabilitycited by 10

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 0; 2025: 2.

6 papers.

  1. 2023Federated Quantum Machine Learning with Differential Privacycited by 17
  2. 2023Quantum Pufferfish Privacy: A Flexible Privacy Framework for Quantum Systemscited by 9
  3. 2023Detecting Violations of Differential Privacy for Quantum Algorithmscited by 3
  4. 2025Adversarial Robustness in Distributed Quantum Machine Learningcited by 2
  5. 2025Non-Linear Strong Data-Processing for Quantum Hockey-Stick Divergencescited by 1
  6. 2022Unclonability and Quantum Cryptanalysis: From Foundations to Applicationscited by 0