GPM: The Gaussian Pancake Mechanism for Planting Undetectable Backdoors in Differential Privacy
Summary: Introduces GPM, a Gaussian mechanism backdoor computationally indistinguishable from standard GM yet offering arbitrarily weaker statistical DP. Proves covertness and leakage, with near-perfect distinguishing attacks, exposing implementation-level privacy compromises. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Haochen Sun (University of Waterloo)
- 2. Xi He (University of Waterloo)
BibTeX Citation
@inproceedings{sun_sigmod26,
title = {{GPM: The Gaussian Pancake Mechanism for Planting Undetectable Backdoors in Differential Privacy}},
author = {Sun, Haochen and He, Xi},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802068},
url = {https://dl.acm.org/doi/10.1145/3802068},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 121 | Boosting the Accuracy of Differentially Private Histograms Through Consistency | 2010 | VLDB | 0.00031524261 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 5,270 | Functional Mechanism: Regression Analysis under Differential Privacy | 2012 | VLDB |
| 2 | 6,468 | Differential Privacy in Data Publication and Analysis | 2012 | SIGMOD |
| 3 | 10,523 | Privacy Loss of Noise Perturbation via Concentration Analysis of A Product Measure | 2026 | SIGMOD |
| 4 | 3,125 | CGM: An Enhanced Mechanism for Streaming Data Collection with Local Differential Privacy | 2021 | VLDB |
| 5 | 10,988 | Calibrating Noise for Group Privacy in Subsampled Mechanisms | 2025 | VLDB |
| 6 | 10,587 | Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing | 2026 | VLDB |
| 7 | 5,585 | Practical Differential Privacy via Grouping and Smoothing | 2013 | VLDB |
| 8 | 8,288 | Privately Answering Queries on Skewed Data via Per-Record Differential Privacy | 2024 | VLDB |
| 9 | 3,396 | Bayesian Differential Privacy on Correlated Data | 2015 | SIGMOD |
| 10 | 10,376 | A General Framework for Per-record Differential Privacy | 2026 | SIGMOD |