PACE: Poisoning Attacks on Learned Cardinality Estimation
Summary: PACE enables black-box poisoning of learned cardinality estimators, causing significant accuracy degradation. It uses a surrogate to approximate the model, solves a two-variable poisoning optimization, and trains a poison generator with an anomaly detector to mimic workload. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jintao Zhang (Tsinghua University)
- 2. Chao Zhang (Tsinghua University)
- 3. Guoliang Li (Tsinghua University)
- 4. Chengliang Chai (Beijing Institute of Technology)
BibTeX Citation
@inproceedings{zhang_sigmod24,
title = {{PACE: Poisoning Attacks on Learned Cardinality Estimation}},
author = {Zhang, Jintao and Zhang, Chao and Li, Guoliang and Chai, Chengliang},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3639292},
url = {https://dl.acm.org/doi/10.1145/3639292},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,599 | Understanding Robustness Issues of Updatable Learned Indexes: [Experiments & Analysis] | 2026 | SIGMOD | 5.2492748e-05 |
| 10,267 | Mathematical Foundations of Poisoning Attacks on Linear Regression over Cumulative Distribution Functions | 2026 | SIGMOD | 5.093636e-05 |
| 10,851 | ACE: A Cardinality Estimator for Set-Valued Queries | 2025 | VLDB | 5.093636e-05 |
| 11,083 | Graph Transformers for Query Plan Representation: Potentials and Challenges | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 26 of 26 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next