Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
While significant progress has been made separately on analytics systems for scalable stochastic gradient descent (SGD) and private SGD, none of the major scalable analytics frameworks have incorporated differentially private SGD. There are two inter-related issues for this disconnect between research and practice: (1) low model accuracy due to added noise to guarantee privacy, and (2) high development and runtime overhead of the private algorithms. This paper takes a first step to remedy this disconnect and proposes a private SGD algorithm to address both issues in an integrated manner. In contrast to the white-box approach adopted by previous work, we revisit and use the classical technique of output perturbation to devise a novel ``bolt-on'' approach to private SGD. While our approach trivially addresses (2), it makes (1) even more challenging. We address this challenge by providing a novel analysis of the L2-sensitivity of SGD, which allows, under the same privacy guarantees, better convergence of SGD when only a constant number of passes can be made over the data. We integrate our algorithm, as well as other state-of-the-art differentially private SGD, into Bismarck, a popular scalable SGD-based analytics system on top of an RDBMS. Extensive experiments show that our algorithm can be easily integrated, incurs virtually no overhead, scales well, and most importantly, yields substantially better (up to 4X) test accuracy than the state-of-the-art algorithms on many real datasets.
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.
Integrity signals
Registry
Cites
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.
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
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Parikh, N., & Boyd, S. (2014) · Foundations and Trends® in Optimization · doi:10.1561/2400000003 · Cited by 4,102
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
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
Cited by
Does learning require memorization? a short tale about a long tail
Feldman, V. (2020) · Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing · doi:10.1145/3357713.3384290 · Cited by 287
“The best results (that we are aware of) on modern benchmarks that are achieved without interpolation are those for differentially private (DP) training algorithms [Aba+16; PAEGT16; PAEGT17; MRTZ18].”
BackgroundEvaluating Differentially Private Machine Learning in Practice
Jayaraman, B., & Evans, D. (2019) · arXiv · doi:10.48550/arxiv.1902.08874 · Cited by 265
Generative Models for Effective ML on Private, Decentralized Datasets
Augenstein, S., McMahan, H. B., Ramage, D., Ramaswamy, S., Kairouz, P., Chen, M., Mathews, R., & Arcas, B. A. Y. (2019) · arXiv · doi:10.48550/arxiv.1911.06679 · Cited by 103
“Most prior work on differentially private ML (e.g. Chaudhuri et al. (2011); Bassily et al. (2014); Abadi et al. (2016); Wu et al. (2017); Papernot et al. (2017)) deals with example-level privacy: two datasets d and d′ are defined to be adjacent if d′ can be formed by adding or removing a single…”
BackgroundPrivacy Amplification by Iteration
Feldman, V., Mironov, I., Talwar, K., & Thakurta, A. (2018) · 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS) · doi:10.1109/focs.2018.00056 · Cited by 80
Survey: Leakage and Privacy at Inference Time
Jegorova, M., Kaul, C., Mayor, C., O'Neil, A. Q., Weir, A., Murray-Smith, R., & Tsaftaris, S. A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3229593 · Cited by 77
Metadata
- Authors
- Wu, X., Li, F., Kumar, A., Chaudhuri, K., Jha, S., & Naughton, J.
- Venue
- Proceedings of the 2017 ACM International Conference on Management of Data
- Publisher
- ACM
- Published
- 2017-05-09
- Pages
- 1307-1322
- OpenAlex
- W2963999993
- Cited by
- 175
- References
- 4
- FWCI
- 9.02
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics. https://app.cochat.ai/papers/10.1145/3035918.3064047
- The paper
- Wu, X., Li, F., Kumar, A., Chaudhuri, K., Jha, S., & Naughton, J. (2017). Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics. Proceedings of the 2017 ACM International Conference on Management of Data. https://doi.org/10.1145/3035918.3064047
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.