CoChat

On the Protection of Private Information in Machine Learning Systems: Two Recent Approches

Open access
Abadi, Martin, Erlingsson, Ulfar, Goodfellow, Ian, McMahan, H. Brendan, Mironov, Ilya, Papernot, Nicolas, Talwar, Kunal, Zhang, Li · 2017 · 2017 IEEE 30th Computer Security Foundations Symposium (CSF)
Cited by 39

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Abstract

The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving privacy. However, older ideas about privacy may well remain valid and useful. This note reviews two recent works on privacy in the light of the wisdom of some of the early literature, in particular the principles distilled by Saltzer and Schroeder in the 1970s.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/csf.2017.10

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

  • Deep learning

    LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126

  • Membership Inference Attacks Against Machine Learning Models

    Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · cited 1×

    “Attacks may have at least two distinct goals, illustrated by the work of Fredrikson et al. [20] and that of Shokri et al. [21], respectively: • the extraction of training data (total or partial) from a model g , or • testing whether an input-output pair, or simply an input or an output, is part of…”
    Background
  • Privacy-preserving deep learning

    Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 1×

    “, [11], [12], [13], [14], [15], [16], [17], [18]), and undoubtedly neither noisy SGD nor PATE constitutes the last word on the subject; surveying this research is beyond the scope of this note.”
    Background
  • The protection of information in computer systems

    Saltzer, J. H., & Schroeder, M. D. (1975) · Proceedings of the IEEE · doi:10.1109/proc.1975.9939 · Cited by 2,126 · cited 1×

    “In their classic tutorial paper, Saltzer and Schroeder described the mechanics of protecting information in computer systems, as it was understood in the mid 1970s [1].”
    Background
  • RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response

    Erlingsson, Ú., Pihur, V., & Korolova, A. (2014) · Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2660267.2660348 · Cited by 1,838

    Self-citation
  • Our Data, Ourselves: Privacy Via Distributed Noise Generation

    Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., & Naor, M. (2006) · Lecture Notes in Computer Science · doi:10.1007/11761679_29 · Cited by 1,835 · cited 1×

    “We note, however, that many of these techniques achieve a guarantee known as ( , δ)-differential-privacy [35]; while the parameter from the original definition of differential privacy can be viewed as a privacy cost [9], the additional parameter δ can be viewed as a probability of failure.”
    BackgroundSelf-citation
  • Rényi Differential Privacy

    Mironov, I. (2017) · 2017 IEEE 30th Computer Security Foundations Symposium (CSF) · doi:10.1109/csf.2017.11 · Cited by 1,255 · cited 1×

    “A more refined analysis paints a subtle and interesting picture with a trade-off between the parameters and δ [36].”
    BackgroundSelf-citation
  • What can we learn privately?

    Kasiviswanathan, S. P., Lee, H. K., Nissim, K., Raskhodnikova, S., & Smith, A. (2011) · SIAM Journal on Computing · doi:10.1137/090756090 · Cited by 898 · cited 1×

    “, [11], [12], [13], [14], [15], [16], [17], [18]), and undoubtedly neither noisy SGD nor PATE constitutes the last word on the subject; surveying this research is beyond the scope of this note.”
    Background
  • Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

    Papernot, N., Abadi, M., Erlingsson, Ú., Goodfellow, I., & Talwar, K. (2016) · arXiv · doi:10.48550/arxiv.1610.05755 · Cited by 492

    Self-citation

Cited by

See all 39

Metadata

Authors
Abadi, M., Erlingsson, U., Goodfellow, I., McMahan, H. B., Mironov, I., Papernot, N., Talwar, K., & Zhang, L.
Venue
2017 IEEE 30th Computer Security Foundations Symposium (CSF)
Publisher
IEEE
Published
2017-08
Pages
1-6
ISSN
1063-6900 (ISSN-L)
OpenAlex
W2751384916
Cited by
39
References
9
FWCI
2.92
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.