mlsanityData to 7 Oct 2026

Data Poisoning Attacks against Online Learning

arXiv 1808.08994 ↗First posted 27 Aug 2018cs.LG stat.MLcited by 24

Not on the map. Why?

Abstract (arXiv)

We consider data poisoning attacks, a class of adversarial attacks on machine learning where an adversary has the power to alter a small fraction of the training data in order to make the trained classifier satisfy certain objectives. While there has been much prior work on data poisoning, most of it is in the offline setting, and attacks for online learning, where training data arrives in a streaming manner, are not well understood. In this work, we initiate a systematic investigation of data poisoning attacks for online learning. We formalize the problem into two settings, and we propose a general attack strategy, formulated as an optimization problem, that applies to both with some modifications. We propose three solution strategies, and perform extensive experimental evaluation. Finally, we discuss the implications of our findings for building successful defenses.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2019: 1; 2020: 0; 2021: 7; 2022: 6; 2023: 4; 2024: 2; 2025: 4.

24 papers.

Sort:

By area:

  1. 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
  2. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearningcited by 47
  3. 2022Data Poisoning Attacks Against Multimodal Encoderscited by 41
  4. 2022Understanding Rare Spurious Correlations in Neural Networkscited by 27
  5. 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networkscited by 19
  6. 2022System Cards for AI-Based Decision-Making for Public Policycited by 11
  7. 2021Accumulative Poisoning Attacks on Real-time Datacited by 10
  8. 2023Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoningcited by 10
  9. 2021FooBaR: Fault Fooling Backdoor Attack on Neural Network Trainingcited by 6
  10. 2022FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Datacited by 5
  11. 2021Robust Online Convex Optimization in the Presence of Outlierscited by 4
  12. 2025Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoningcited by 3
12 more
  1. 2021Influence Based Defense Against Data Poisoning Attacks in Online Learningcited by 2
  2. 2022On the Permanence of Backdoors in Evolving Modelscited by 2
  3. 2024On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMscited by 2
  4. 2023PACOL: Poisoning Attacks Against Continual Learnerscited by 1
  5. 2025On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabelingcited by 1
  6. 2021Gradient-based Data Subversion Attack Against Binary Classifierscited by 0
  7. 2022Adversarial Patterns: Building Robust Android Malware Classifierscited by 0
  8. 2023Attacks on Online Learners: a Teacher-Student Analysiscited by 0
  9. 2023Exploring Model Dynamics for Accumulative Poisoning Discoverycited by 0
  10. 2024Transfer-based Adversarial Poisoning Attacks for Online (MIMO-)Deep Recevierscited by 0
  11. 2025Fake or Real: The Impostor Hunt in Texts for Space Operationscited by 0
  12. 2025FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairnesscited by 0