mlsanityData to 14 Oct 2026

Online AutoML: Evaluating Poisoning Attacks on Cost-Utility Adversarial Training Defence Strategy for IoT Networks

arXiv 2610.05810 ↗First posted 5 Oct 2026cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine learning (ML)-powered poisoning attack vectors are adversarial maneuvers whereby an attacker intentionally inserts, corrupts, or alters training data to distort an ML model's learning process. The objective is to diminish model efficacy, instill biases, induce misclassifications, or include concealed backdoors that may be attacked during implementation. In streaming contexts, poisoning attacks pose significant risks since models perpetually update based on incoming streams of data. An assailant may incrementally introduce harmful samples into this data stream, leading the model to assimilate erroneous features over time without timely identification. Therefore, this study is aimed at evaluating the efficacy of the adversarial training (AT) defense approach against poisoning attacks (label flip and noise injection) using an online AutoML pipeline for Internet of Things (IoT) networks. Specifically, poisoning attacks (label flip and noise injection) were applied to streaming-capable AutoML learners (Hoeffding Tree (HT), Leveraging Bagging (LB), Adaptive Random Forest (ARF), Hoeffding Adaptive Tree (HAT), and Streaming Random Patches (SRP)). Under the strongest poisoning rate (PR = 1.0), AT-SRP achieved the highest F1-score against label flip poisoning (0.904), while AT-LB achieved the highest F1-score against noise-injection poisoning (0.933). Finally, several drift detection methods were used for rolling accuracy and prequential evaluation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 26 references that are in the map. First posted on arXiv 5 Oct 2026.

Builds on

14 of 26 references.

References · 14

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  4. 2020Certified Robustness to Label-Flipping Attacks via Randomized Smoothingcited by 108
  5. 2020River: machine learning for streaming data in Pythoncited by 98
  6. 2020Data Poisoning Attacks on Federated Machine Learningcited by 62
  7. 2017On the Reliable Detection of Concept Drift from Streaming Unlabeled Datacited by 33
  8. 2019On Defending Against Label Flipping Attacks on Malware Detection Systemscited by 22
  9. 2022IoT Data Analytics in Dynamic Environments: From An Automated Machine Learning Perspectivecited by 16
  10. 2017SCARFF: a Scalable Framework for Streaming Credit Card Fraud Detection with Sparkcited by 15
  11. 2022Adversarial Robustness for Tabular Data through Cost and Utility Awarenesscited by 15
  12. 2023Analysis of Label-Flip Poisoning Attack on Machine Learning Based Malware Detectorcited by 11
2 more
  1. 2020Machine Learning (In) Security: A Stream of Problemscited by 8
  2. 2025Enabling AutoML for Zero-Touch Network Security: Use-Case Driven Analysiscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Survey
  2. 2026Robustness Analysis of Machine Learning Models for IoT Intrusion Detection Under Data Poisoning Attacks
  3. 2022Machine Learning Security against Data Poisoning: Are We There Yet?
  4. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
  5. 2021De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks
  6. 2021Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors
  7. 2021What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning
  8. 2024Have You Poisoned My Data? Defending Neural Networks against Data Poisoning