Back to papers
Robustness of Updatable Learning-based Index Advisors against Poisoning Attack
Summary: Introduces PIPA, an opaque-box stress-test framework to evaluate the robustness of updatable learning-based Index Advisors against poisoning attacks without using private data. Probing, injecting, and IABART-based query generation reveal systemic non-robustness: subtle extraneous workloads can demote top indexes and trap IAs in local optima even after fine-tuning.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 6820
- Venue
- SIGMOD
- Year
- 2024
- Pagerank
- 4.2539423e-05
- Overall Rank
- 9,901 | 31.19%
- DOI
-
10.1145/3639265
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 237 |
An Efficient, Cost-Driven Index Selection Tool for Microsoft SQL Server |
1997 |
VLDB |
0.00031727601 |
| 405 |
Massive Stochastic Testing of SQL |
1998 |
VLDB |
0.00024046204 |
| 1,018 |
Automatic Physical Database Tuning: A Relaxation-based Approach |
2005 |
SIGMOD |
0.00014626746 |
| 1,856 |
AI Meets AI: Leveraging Query Executions to Improve Index Recommendations |
2019 |
SIGMOD |
0.00010319105 |
| 2,022 |
Magic mirror in my hand, which is the best in the land? An Experimental Evaluation of Index Selection Algorithms |
2020 |
VLDB |
9.7623022e-05 |
| 2,280 |
Generating Targeted Queries for Database Testing |
2008 |
SIGMOD |
9.1247368e-05 |
| 5,289 |
LearnedSQLGen: Constraint-aware SQL Generation using Reinforcement Learning |
2022 |
SIGMOD |
5.5790771e-05 |
| 5,310 |
The Price of Tailoring the Index to Your Data: Poisoning Attacks on Learned Index Structures |
2022 |
SIGMOD |
5.5713508e-05 |
| 5,673 |
Budget-aware Index Tuning with Reinforcement Learning |
2022 |
SIGMOD |
5.3789277e-05 |
| 6,364 |
ISUM: Efficiently Compressing Large and Complex Workloads for Scalable Index Tuning |
2022 |
SIGMOD |
5.0895007e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 8,198 |
Leveraging Dynamic and Heterogeneous Workload Knowledge to Boost the Performance of Index Advisors |
2024 |
VLDB |
4.556207e-05 |
| 1,438 |
Benchmarking Learned Indexes |
2021 |
VLDB |
0.00011965956 |
| 5,673 |
Budget-aware Index Tuning with Reinforcement Learning |
2022 |
SIGMOD |
5.3789277e-05 |
| 5,072 |
Learned Index: A Comprehensive Experimental Evaluation |
2023 |
VLDB |
5.7121108e-05 |
| 8,668 |
Algorithmic Complexity Attacks on Dynamic Learned Indexes |
2024 |
VLDB |
4.4671214e-05 |
| 4,056 |
Are Updatable Learned Indexes Ready? |
2022 |
VLDB |
6.4905689e-05 |
| 6,753 |
Breaking It Down: An In-depth Study of Index Advisors |
2024 |
VLDB |
4.9345582e-05 |
| 5,310 |
The Price of Tailoring the Index to Your Data: Poisoning Attacks on Learned Index Structures |
2022 |
SIGMOD |
5.5713508e-05 |
| 10,087 |
High Performance or Low Memory? An Updatable Learned Index Framework for Time-Space Tradeoff |
2026 |
SIGMOD |
4.1905499e-05 |
| 10,038 |
Understanding Robustness Issues of Updatable Learned Indexes: [Experiments & Analysis] |
2026 |
SIGMOD |
4.1905499e-05 |