# Data Poisoning Attacks on Regression Learning and Corresponding Defenses

arXiv: https://arxiv.org/abs/2009.07008 · HTML: https://mlsanity.com/paper/2009.07008/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2020.

## Built on by (most cited first, 11 of 11)

- [Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning](https://mlsanity.com/paper/2205.01992/) (2022)
- [The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions](https://mlsanity.com/paper/2304.10655/) (2023)
- [Certifying Data-Bias Robustness in Linear Regression](https://mlsanity.com/paper/2206.03575/) (2022)
- [The poison of dimensionality](https://mlsanity.com/paper/2409.17328/) (2024)
- [Evasion Attacks Against Bayesian Predictive Models](https://mlsanity.com/paper/2506.09640/) (2025)
- [Safety-Efficacy Trade Off: Robustness against Data-Poisoning](https://mlsanity.com/paper/2602.00822/) (2026)
- [Testing the Robustness of Learned Index Structures](https://mlsanity.com/paper/2207.11575/) (2022)
- [Learning from Uncertain Data: From Possible Worlds to Possible Models](https://mlsanity.com/paper/2405.18549/) (2024)
- [LOGSAFE: Logic-Guided Verification for Trustworthy Federated Time-Series Learning](https://mlsanity.com/paper/2411.03231/) (2024)
- [Defending Against Neural Network Model Inversion Attacks via Data Poisoning](https://mlsanity.com/paper/2412.07575/) (2024)
- [Stealthy Poisoning Attacks Bypass Defenses in Regression Settings](https://mlsanity.com/paper/2601.22308/) (2026)

## Abstract (arXiv)

Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset. So far, it has been studied mostly for classification, even though regression learning is used in many mission critical systems (such as dosage of medication, control of cyber-physical systems and managing power supply). Therefore, in the present research, we aim to evaluate all aspects of data poisoning attacks on regression learning, exceeding previous work both in terms of breadth and depth. We present realistic scenarios in which data poisoning attacks threaten production systems and introduce a novel black-box attack, which is then applied to a real-word medical use-case. As a result, we observe that the mean squared error (MSE) of the regressor increases to 150 percent due to inserting only two percent of poison samples. Finally, we present a new defense strategy against the novel and previous attacks and evaluate it thoroughly on 26 datasets. As a result of the conducted experiments, we conclude that the proposed defence strategy effectively mitigates the considered attacks.