From Zero to Hero: Detecting Leaked Data through Synthetic Data Injection and Model Querying
Summary: LDSS detects unauthorized training-data leakage without attacker-side access or training-process control. It injects a small set of locally class-shifted synthetic tuples, then identifies leaked-data models via prediction queries, remaining model-oblivious across classifiers and regression. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Biao Wu (National University of Singapore)
- 2. Qiang Huang (National University of Singapore)
- 3. Anthony K. H. Tung (National University of Singapore)
BibTeX Citation
@article{wu_vldb24,
title = {{From Zero to Hero: Detecting Leaked Data through Synthetic Data Injection and Model Querying}},
author = {Wu, Biao and Huang, Qiang and Tung, Anthony K. H.},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {8},
pages = {1898--1910},
doi = {10.14778/3659437.3659446},
url = {https://doi.org/10.14778/3659437.3659446},
year = {2024}
}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 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,279 | Locality-Sensitive Hashing Scheme based on Longest Circular Co-Substring | 2020 | SIGMOD | 7.5711218e-05 |
| 5,121 | Point-to-Hyperplane Nearest Neighbor Search Beyond the Unit Hypersphere | 2021 | SIGMOD | 6.3577317e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,349 | DP-PQD: Privately Detecting Per-Query Gaps In Synthetic Data Generated By Black-Box Mechanisms | 2024 | VLDB |
| 2 | 8,908 | Privacy and Accuracy-Aware AI/ML Model Deduplication | 2025 | SIGMOD |
| 3 | 7,909 | Differentially Private Data Generation with Missing Data | 2024 | VLDB |
| 4 | 10,254 | HeteroFedSyn: Differentially Private Tabular Data Synthesis for Heterogeneous Federated Settings | 2026 | SIGMOD |
| 5 | 7,841 | Quantifying identifiability to choose and audit epsilon in differentially private deep learning | 2021 | VLDB |
| 6 | 5,131 | Enabling SQL-based Training Data Debugging for Federated Learning | 2022 | VLDB |
| 7 | 3,016 | Plausible Deniability for Privacy-Preserving Data Synthesis | 2017 | VLDB |
| 8 | 10,345 | Benchmarking Differentially Private Tabular Data Synthesis: [Experiments & Analysis] | 2026 | SIGMOD |
| 9 | 2,129 | Data Synthesis based on Generative Adversarial Networks | 2018 | VLDB |
| 10 | 8,514 | Synthetic Tabular Data: Methods, Attacks and Defenses | 2025 | VLDB |