mlsanityData to 14 Oct 2026

Machine Learning Security against Data Poisoning: Are We There Yet?

arXiv 2204.05986 ↗First posted 12 Apr 2022cs.CR cs.CVcited by 23

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised when such data is maliciously manipulated to mislead the learning process. In this article, we first review poisoning attacks that compromise the training data used to learn ML models, including attacks that aim to reduce the overall performance, manipulate the predictions on specific test samples, and even implant backdoors in the model. We then discuss how to mitigate these attacks using basic security principles, or by deploying ML-oriented defensive mechanisms. We conclude our article by formulating some relevant open challenges which are hindering the development of testing methods and benchmarks suitable for assessing and improving the trustworthiness of ML models against data poisoning attacks

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 12 of its 37 references that are in the map. First posted on arXiv 12 Apr 2022.

Builds on

12 of 37 references.

References · 12

  1. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  2. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  3. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  4. 2017Certified Defenses for Data Poisoning Attackscited by 303
  5. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 197
  6. 2019Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detectioncited by 124
  7. 2020Adversarial Machine Learning -- Industry Perspectivescited by 122
  8. 2020On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shapingcited by 83
  9. 2019Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encodercited by 70
  10. 2020Subpopulation Data Poisoning Attackscited by 70
  11. 2020Poisoning Attacks on Algorithmic Fairnesscited by 59
  12. 2022Energy-Latency Attacks via Sponge Poisoningcited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 4; 2025: 9; 2026: 3.

23 papers.

Sort:

By area:

  1. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 94
  2. 2025A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memorycited by 67
  3. 2023Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attackscited by 33
  4. 2025Data Poisoning in Deep Learning: A Surveycited by 20
  5. 2023Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoningcited by 10
  6. 2025Position: Bridge the Gaps between Machine Unlearning and AI Regulationcited by 7
  7. 2024Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Codecited by 6
  8. 2024Exact Certification of (Graph) Neural Networks Against Label Poisoningcited by 6
  9. 2025LLM Misalignment via Adversarial RLHF Platformscited by 5
  10. 2023Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Trainingcited by 3
  11. 2025Automatic Grid Updates for Kolmogorov-Arnold Networks using Layer Histogramscited by 3
  12. 2023Hardening RGB-D Object Recognition Systems against Adversarial Patch Attackscited by 2
11 more
  1. 2025False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systemscited by 2
  2. 2023Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelinescited by 1
  3. 2024Federated Learning in Adversarial Environments: Testbed Design and Poisoning Resilience in Cybersecuritycited by 1
  4. 2023Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomycited by 0
  5. 2024Sonic: Fast and Transferable Data Poisoning on Clustering Algorithmscited by 0
  6. 2025Task-Agnostic Federation over Decentralized Data: Research Landscape and Visionscited by 0
  7. 2025How to Protect Models against Adversarial Unlearning?cited by 0
  8. 2025Defending Against Beta Poisoning Attacks in Machine Learning Modelscited by 0
  9. 2026Topology-Independent Robustness of the Weighted Mean under Label Poisoning Attacks in Heterogeneous Decentralized Learningcited by 0
  10. 2026RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalancecited by 0
  11. 2026Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logisticscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Survey
  2. 2021Preventing Machine Learning Poisoning Attacks Using Authentication and Provenance
  3. 2023Analysis of Label-Flip Poisoning Attack on Machine Learning Based Malware Detector
  4. 2025SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
  5. 2025Detecting and Preventing Data Poisoning Attacks on AI Models
  6. 2022Lethal Dose Conjecture on Data Poisoning
  7. 2023Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
  8. 2022How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?