Pluto: Sample Selection for Robust Anomaly Detection on Polluted Log Data
Summary: Pluto automatically selects a clean subset from polluted log data to train a Transformer-based anomaly detector. It uses Gaussian mixtures to identify and discard polluted embedding regions and a (1−1/e) greedy facility-location approach to purify samples, iterating training. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Lei Ma (Worcester Polytechnic Institute)
- 2. Lei Cao (University of Arizona)
- 3. Peter M. VanNostrand (Worcester Polytechnic Institute)
- 4. Dennis M. Hofmann (Worcester Polytechnic Institute)
- 5. Yao Su (Worcester Polytechnic Institute)
- 6. Elke A. Rundensteiner (Worcester Polytechnic Institute)
BibTeX Citation
@inproceedings{ma_sigmod24,
title = {{Pluto: Sample Selection for Robust Anomaly Detection on Polluted Log Data}},
author = {Ma, Lei and Cao, Lei and VanNostrand, Peter M. and Hofmann, Dennis M. and Su, Yao and Rundensteiner, Elke A.},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3677139},
url = {https://dl.acm.org/doi/10.1145/3677139},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,194 | ANTEATER: A Filter-then-Scrutinize Architecture for End-to-End Attack Investigation | 2026 | SIGMOD | 5.093636e-05 |
| 10,507 | Unseen Anomaly Detection from System Logs | 2026 | SIGMOD | 5.093636e-05 |
| 10,956 | CoLA: Model Collaboration for Log-based Anomaly Detection | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 142 | LOF: Identifying Density-Based Local Outliers | 2000 | SIGMOD | 0.0002962566 |
| 3,376 | Robust and Transferable Log-based Anomaly Detection | 2023 | SIGMOD | 7.4605908e-05 |
| 5,020 | Unsupervised Contextual Anomaly Detection for Database Systems | 2022 | SIGMOD | 6.3987603e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,956 | CoLA: Model Collaboration for Log-based Anomaly Detection | 2025 | VLDB |
| 2 | 5,946 | Streaming Anomaly Detection Using Randomized Matrix Sketching | 2016 | VLDB |
| 3 | 6,141 | An Experimental Evaluation of Anomaly Detection in Time Series | 2024 | VLDB |
| 4 | 10,909 | LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation | 2025 | VLDB |
| 5 | 1,793 | TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data | 2022 | VLDB |
| 6 | 11,099 | MLP-Mixer based Masked Autoencoders Are Effective, Explainable and Robust for Time Series Anomaly Detection | 2025 | VLDB |
| 7 | 5,713 | PreLog: A Pre-trained Model for Log Analytics | 2024 | SIGMOD |
| 8 | 10,507 | Unseen Anomaly Detection from System Logs | 2026 | SIGMOD |
| 9 | 10,019 | Substructure-aware Log Anomaly Detection | 2025 | VLDB |
| 10 | 3,376 | Robust and Transferable Log-based Anomaly Detection | 2023 | SIGMOD |