mlsanityData to 7 Oct 2026

Label Sanitization against Label Flipping Poisoning Attacks

arXiv 1803.00992 ↗First posted 2 Mar 2018stat.ML cs.CR cs.LGcited by 68

Not on the map. Why?

Cited by 29 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an indiscriminate way. Label flipping attacks are a special case of data poisoning, where the attacker can control the labels assigned to a fraction of the training points. Even if the capabilities of the attacker are constrained, these attacks have been shown to be effective to significantly degrade the performance of the system. In this paper we propose an efficient algorithm to perform optimal label flipping poisoning attacks and a mechanism to detect and relabel suspicious data points, mitigating the effect of such poisoning attacks.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 11; 2023: 14; 2024: 13; 2025: 12; 2026: 4.

68 papers.

Sort:

By area:

  1. 2021Trustworthy AI: From Principles to Practicescited by 206
  2. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  3. 2021Sample Selection for Fair and Robust Trainingcited by 48
  4. 2022Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attackscited by 37
  5. 2021DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentationscited by 33
  6. 2022PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learningcited by 33
  7. 2021De-Pois: An Attack-Agnostic Defense against Data Poisoning Attackscited by 29
  8. 2023Label Poisoning is All You Needcited by 27
  9. 2021Certifying Robustness to Programmable Data Bias in Decision Treescited by 21
  10. 2023The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictionscited by 17
  11. 2023Run-Off Election: Improved Provable Defense against Data Poisoning Attackscited by 16
  12. 2023BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learningcited by 16
38 more
  1. 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Surveycited by 15
  2. 2024Preference Poisoning Attacks on Reward Model Learningcited by 14
  3. 2021Robust Android Malware Detection System against Adversarial Attacks using Q-Learningcited by 12
  4. 2023Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systemscited by 10
  5. 2022Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition Systemcited by 9
  6. 2025Self-Consuming Generative Models with Adversarially Curated Datacited by 8
  7. 2023Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Datacited by 6
  8. 2024RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression Taskscited by 6
  9. 2025StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusionscited by 6
  10. 2021EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetrycited by 5
  11. 2022A Survey on Poisoning Attacks Against Supervised Machine Learningcited by 5
  12. 2024Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networkscited by 5
  13. 2024Exact Certification of (Graph) Neural Networks Against Label Poisoningcited by 5
  14. 2025Adversarial Training for Defense Against Label Poisoning Attackscited by 5
  15. 2025LLM Misalignment via Adversarial RLHF Platformscited by 5
  16. 2022Breaking Fair Binary Classification with Optimal Flipping Attackscited by 4
  17. 2022Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learningcited by 4
  18. 2024A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attackscited by 4
  19. 2021Active Learning Under Malicious Mislabeling and Poisoning Attackscited by 3
  20. 2022Certifying Data-Bias Robustness in Linear Regressioncited by 3
  21. 2023Explainable Data Poison Attacks on Human Emotion Evaluation Systems based on EEG Signalscited by 3
  22. 2023Hyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimizationcited by 3
  23. 2023Towards Poisoning Fair Representationscited by 3
  24. 2023Fast Adversarial Label-Flipping Attack on Tabular Datacited by 3
  25. 2024The Effect of Data Poisoning on Counterfactual Explanationscited by 3
  26. 2021Responsible AI Challenges in End-to-end Machine Learningcited by 2
  27. 2021Influence Based Defense Against Data Poisoning Attacks in Online Learningcited by 2
  28. 2022On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approachcited by 2
  29. 2024Combining Machine Learning Defenses without Conflictscited by 2
  30. 2024Adversarial Data Poisoning Attacks on Quantum Machine Learning in the NISQ Eracited by 2
  31. 2021Classification Auto-Encoder based Detector against Diverse Data Poisoning Attackscited by 1
  32. 2022Defend Data Poisoning Attacks on Voice Authenticationcited by 1
  33. 2023Attacking Byzantine Robust Aggregation in High Dimensionscited by 1
  34. 2024Have You Poisoned My Data? Defending Neural Networks against Data Poisoningcited by 1
  35. 2021Defending Against Adversarial Denial-of-Service Data Poisoning Attackscited by 0
  36. 2021A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifierscited by 0
  37. 2021Gradient-based Data Subversion Attack Against Binary Classifierscited by 0
  38. 2023Exploring Model Dynamics for Accumulative Poisoning Discoverycited by 0

50 most cited of 68 All 68 (JSON)