Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.

Mitigating Poisoning Attacks on Machine Learning Models: A Data Provenance Based Approach

Baracaldo, Nathalie, Chen, Bryant, Ludwig, Heiko, Safavi, Jaehoon Amir · 2017 · Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security

Abstract

The use of machine learning models has become ubiquitous. Their predictions are used to make decisions about healthcare, security, investments and many other critical applications. Given this pervasiveness, it is not surprising that adversaries have an incentive to manipulate machine learning models to their advantage. One way of manipulating a model is through a poisoning or causative attack in which the adversary feeds carefully crafted poisonous data points into the training set. Taking advantage of recently developed tamper-free provenance frameworks, we present a methodology that uses contextual information about the origin and transformation of data points in the training set to identify poisonous data, thereby enabling online and regularly re-trained machine learning applications to consume data sources in potentially adversarial environments. To the best of our knowledge, this is the first approach to incorporate provenance information as part of a filtering algorithm to detect causative attacks. We present two variations of the methodology - one tailored to partially trusted data sets and the other to fully untrusted data sets. Finally, we evaluate our methodology against existing methods to detect poison data and show an improvement in the detection rate.

Overview

Integrity signals

Registry

Crossref · 10.1145/3128572.3140450

Cites

17 of 17 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 17 references

Research works printed but not linked: 2

  1. Nicolas Papernot , Patrick McDaniel , Arunesh Sinha , and Michael Wellman . 2016. Towards the science of security and privacy in machine learning. arXiv preprint arXiv:1611.03814 ( 2016 ). Nicolas Papernot, Patrick McDaniel, Arunesh Sinha, and Michael Wellman. 2016. Towards the science of security and privacy in machine learning. arXiv preprint arXiv:1611.03814 (2016). · arXiv
  2. Mohammed Rangwala , Zhengli Liang , Wei Peng , Xukai Zou , and Feng Li. 2014. A Mutual Agreement Signature Scheme for Secure Data Provenance. environments Vol. 13 ( 2014 ), 14. Mohammed Rangwala, Zhengli Liang, Wei Peng, Xukai Zou, and Feng Li. 2014. A Mutual Agreement Signature Scheme for Secure Data Provenance. environments Vol. 13 (2014), 14.

Cited by

See all 119

Metadata

Authors
Baracaldo, N., Chen, B., Ludwig, H., & Safavi, J. A.
Affiliations
IBM (United States) (US)
Venue
Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security
Publisher
ACM
Published
2017-11-03
Pages
103-110
OpenAlex
W2765325683
Cited by
108
References
17
Citations by year
2026: 7 · 2025: 14 · 2024: 14 · 2023: 14 · 2022: 12 · 2021: 16 · 2020: 14 · 2019: 13 · 2018: 4
FWCI
3.87
Type
conference paper
Language
en
Open access
closed
Locations
ACM Workshop on Artificial Intelligence and Security (AISec) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Hardware and Architecture › Security and Verification in Computing
Keywords
poisoning attacks, adversarial learning, poison detection, data provenance, data filtering, online retraining, training data integrity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Mitigating Poisoning Attacks on Machine Learning Models: A Data Provenance Based Approach. https://app.cochat.ai/papers/10.1145/3128572.3140450
The paper
Baracaldo, N., Chen, B., Ludwig, H., & Safavi, J. A. (2017). Mitigating Poisoning Attacks on Machine Learning Models: A Data Provenance Based Approach. Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security. https://doi.org/10.1145/3128572.3140450

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.