mlsanityData to 14 Oct 2026

Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning

arXiv 1804.00308 ↗First posted 1 Apr 2018cs.CR cs.GT cs.LGcited by 225

Not on the map. Why?

Cited by 40 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of poisoning attacks and their countermeasures for linear regression models. In poisoning attacks, attackers deliberately influence the training data to manipulate the results of a predictive model. We propose a theoretically-grounded optimization framework specifically designed for linear regression and demonstrate its effectiveness on a range of datasets and models. We also introduce a fast statistical attack that requires limited knowledge of the training process. Finally, we design a new principled defense method that is highly resilient against all poisoning attacks. We provide formal guarantees about its convergence and an upper bound on the effect of poisoning attacks when the defense is deployed. We evaluate extensively our attacks and defenses on three realistic datasets from health care, loan assessment, and real estate domains.

Key facts. Cited by 225 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 49; 2022: 46; 2023: 37; 2024: 42; 2025: 32; 2026: 19.

225 papers.

Sort:

By area:

  1. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 290
  2. 2023Towards Unbounded Machine Unlearningcited by 268
  3. 2021Graph Unlearningcited by 138
  4. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 118
  5. 2022Truth Serum: Poisoning Machine Learning Models to Reveal Their Secretscited by 101
  6. 2021Hidden Backdoors in Human-Centric Language Modelscited by 90
  7. 2022Towards Adversarial Evaluations for Inexact Machine Unlearningcited by 84
  8. 2022Recommendation Unlearningcited by 80
  9. 2021Manipulating SGD with Data Ordering Attackscited by 74
  10. 2021Bad Characters: Imperceptible NLP Attackscited by 71
  11. 2021Membership Inference Attacks Against Recommender Systemscited by 57
  12. 2021Poison Ink: Robust and Invisible Backdoor Attackcited by 50
38 more
  1. 2022Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experimentscited by 50
  2. 2021Poisoning the Unlabeled Dataset of Semi-Supervised Learningcited by 44
  3. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 44
  4. 2022Data Poisoning Attacks Against Multimodal Encoderscited by 41
  5. 2021Quantifying and Mitigating Privacy Risks of Contrastive Learningcited by 36
  6. 2024Advances and Open Challenges in Federated Foundation Modelscited by 36
  7. 2022Robust Unlearnable Examples: Protecting Data Against Adversarial Learningcited by 35
  8. 2022Amplifying Membership Exposure via Data Poisoningcited by 34
  9. 2021De-Pois: An Attack-Agnostic Defense against Data Poisoning Attackscited by 33
  10. 2024Teach LLMs to Phish: Stealing Private Information from Language Modelscited by 32
  11. 2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 31
  12. 2022SNAP: Efficient Extraction of Private Properties with Poisoningcited by 31
  13. 2021Machine learning pipeline for battery state of health estimationcited by 29
  14. 2025Traceback of Poisoning Attacks to Retrieval-Augmented Generationcited by 28
  15. 2022Auditing Membership Leakages of Multi-Exit Networkscited by 27
  16. 2023A Survey on Decentralized Federated Learningcited by 27
  17. 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
  18. 2025Data Poisoning in Deep Learning: A Surveycited by 20
  19. 2021Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model's Complexitycited by 19
  20. 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networkscited by 19
  21. 2021Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputscited by 18
  22. 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
  23. 2024Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Modelscited by 18
  24. 2024Poison-splat: Computation Cost Attack on 3D Gaussian Splattingcited by 18
  25. 2023The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictionscited by 17
  26. 2021Security and Privacy for Artificial Intelligence: Opportunities and Challengescited by 16
  27. 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Surveycited by 16
  28. 2022Defending against the Label-flipping Attack in Federated Learningcited by 16
  29. 2022Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Freecited by 15
  30. 2022FL-Defender: Combating Targeted Attacks in Federated Learningcited by 15
  31. 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
  32. 2024A Survey on Machine Unlearning: Techniques and New Emerged Privacy Riskscited by 15
  33. 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 15
  34. 2021Poisoning Attack against Estimating from Pairwise Comparisonscited by 14
  35. 2021Get a Model! Model Hijacking Attack Against Machine Learning Modelscited by 14
  36. 2024Trustworthy Distributed AI Systems: Robustness, Privacy, and Governancecited by 14
  37. 2024Preference Poisoning Attacks on Reward Model Learningcited by 14
  38. 2021Untargeted Poisoning Attack Detection in Federated Learning via Behavior Attestationcited by 13

50 most cited of 225 All 225 (JSON)