The Price of Tailoring the Index to Your Data: Poisoning Attacks on Learned Index Structures
Summary: First study of data poisoning on learned index structures, training on a CDF causing cascading errors across the model. Attacks on RMI and two-stage models yield up to 300x and 3000x error inflation, revealing security risks of data-tailored indexes. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Evgenios M. Kornaropoulos (George Mason University)
- 2. Silei Ren (Cornell University)
- 3. Roberto Tamassia (Brown University)
BibTeX Citation
@inproceedings{kornaropoulos_sigmod22,
title = {{The Price of Tailoring the Index to Your Data: Poisoning Attacks on Learned Index Structures}},
author = {Kornaropoulos, Evgenios M. and Ren, Silei and Tamassia, Roberto},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3517867},
url = {https://dl.acm.org/doi/10.1145/3514221.3517867},
year = {2022}
}
Incoming Citations (Sorted by Pagerank)
Showing 12 of 12 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 15 of 15 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 847 | Benchmarking Learned Indexes | 2021 | VLDB |
| 2 | 3,792 | Learned Index: A Comprehensive Experimental Evaluation | 2023 | VLDB |
| 3 | 4,643 | Learned Index Benefits: Machine Learning Based Index Performance Estimation | 2022 | VLDB |
| 4 | 10,378 | High Performance or Low Memory? An Updatable Learned Index Framework for Time-Space Tradeoff | 2026 | SIGMOD |
| 5 | 8,643 | PACE: Poisoning Attacks on Learned Cardinality Estimation | 2024 | SIGMOD |
| 6 | 6,163 | A Critical Analysis of Recursive Model Indexes | 2022 | VLDB |
| 7 | 43 | The Case for Learned Index Structures | 2018 | SIGMOD |
| 8 | 9,490 | Robustness of Updatable Learning-based Index Advisors against Poisoning Attack | 2024 | SIGMOD |
| 9 | 8,039 | Algorithmic Complexity Attacks on Dynamic Learned Indexes | 2024 | VLDB |
| 10 | 10,267 | Mathematical Foundations of Poisoning Attacks on Linear Regression over Cumulative Distribution Functions | 2026 | SIGMOD |