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
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
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“A number of practical tools, techniques and frameworks have been developed to used for procting data used in ML [79-81, 84, 85] some of which allow a degree of transparency to the applied privacy processes [78].”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [85]
Citations
Cites
Poisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331 · cited 5×
“We also assessed our defense under poisonous data generated by the method presented by Biggio et. al [6].”
BackgroundMethodInfluentialThe security of machine learning
Barreno, M., Nelson, B., Joseph, A. D., & Tygar, J. D. (2010) · Machine Learning · doi:10.1007/s10994-010-5188-5 · Cited by 817 · cited 2×
“Existing approaches to identify poison data points focus on analyzing only the data received for training, and a survey can be found in [3].”
BackgroundExploiting machine learning to subvert your spam filter
Nelson, B. A., Barreno, M., Chi, F. J., Joseph, A. D., Rubinstein, B. I. P., Saini, U., Sutton, C. A., Tygar, J. D., & Xia, K. (2008) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 481
Support Vector Machines Under Adversarial Label Noise
Biggio, B., Nelson, B. A., & Laskov, P. (2011) · UNICA IRIS Institutional Research Information System (University of Cagliari) · Cited by 454
Security Evaluation of Pattern Classifiers under Attack
Biggio, B., Fumera, G., & Roli, F. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.57 · Cited by 411
Systematic Poisoning Attacks on and Defenses for Machine Learning in Healthcare
Mozaffari-Kermani, M., Sur-Kolay, S., Raghunathan, A., & Jha, N. K. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2344095 · Cited by 383 · cited 1×
“Similarly, [12] present an attack that targets the labels input into the training system and a threshold based methodology to detect poison that relies on a Kappa statistic.”
BackgroundThe case of the fake Picasso: preventing history forgery with secure provenance
Hasan, R., Sion, R., & Winslett, M. (2009) · Cited by 204
On the Security of Machine Learning in Malware C&C Detection: A Survey
Gardiner, J., & Nagaraja, S. (2016) · ACM Computing Surveys · doi:10.1145/3003816 · Cited by 156
Adversarial support vector machine learning
Zhou, Y., Kantarcıoğlu, M., Thuraisingham, B. M., & Xi, B. (2012) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2339530.2339697 · Cited by 143 · cited 5×
“• We evaluate our method to detect poison data generated by two methods of [6] and [19].”
MethodInfluentialMisleading Learners: Co-opting Your Spam Filter
Nelson, B. A., Barreno, M., Chi, F. J., Joseph, A. D., Rubinstein, B. I. P., Saini, U., Sutton, C. A., Tygar, J. D., & Xia, K. (2009) · Springer eBooks · doi:10.1007/978-0-387-88735-7_2 · Cited by 137 · cited 4×
“The closest related work is Reject On Negative Impact (RONI) methodology proposed by Nelson et al. in [13] and further enhanced in [15], where a calibration methodology to evaluate the performance of a model was included.”
MethodResultInfluential
Research works printed but not linked: 2
- 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
- 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
Data Poisoning Attacks Against Federated Learning Systems
Tolpegin, V., Truex, S., Gursoy, M. E., & Liu, L. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58951-6_24 · Cited by 927
STRIP: a defence against trojan attacks on deep neural networks
Gao, Y., Xu, C., Wang, D., Chen, S., Ranasinghe, D. C., & Nepal, S. (2019) · Proceedings of the 35th Annual Computer Security Applications Conference · doi:10.1145/3359789.3359790 · Cited by 707
Trustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612
“Moreover, recent research has shown that data provenance can be used to mitigate data poisoning [33], thus enhancing the robustness and security of an AI system.”
BackgroundAdversarial Robustness Toolbox v1.0.0
Nicolae, M.-I., Sinn, M., Tran, M. N., Buesser, B., Rawat, A., Wistuba, M., Zantedeschi, V., Baracaldo, N., Chen, B., Ludwig, H., et al. (2018) · arXiv · doi:10.48550/arxiv.1807.01069 · Cited by 594
“The defences parameter is either a string or a list of strings selecting the defences to be applied from the following: – featsqueeze[1-8]? for feature squeezing, where the digit at the end indicates the bit depth (see Section 6.”
BackgroundSelf-citationDetecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
Chen, B., Carvalho, W., Baracaldo, N., Ludwig, H., Edwards, B., Lee, T., Molloy, I., & Srivastava, B. (2018) · arXiv · doi:10.48550/arxiv.1811.03728 · Cited by 485
“Defenses : General defenses against poisoning attacks on supervised learning methods were proposed by Nelson et al. (2009) and Baracaldo et al. (2017).”
MethodSelf-citation
Metadata
- Authors
- Baracaldo, N., Chen, B., Ludwig, H., & Safavi, J. A.
- Affiliations
- IBM (United States) (US)
- ORCID
- Baracaldo, Nathalie
- 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.