• Home
  • Search
  • Resilient automatic model selection for mobility prediction
  • https://doi.org/10.1007/s10586-025-05661-xCopy DOI Icon

Resilient automatic model selection for mobility prediction

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Similar Papers
Abstract

Abstract In order to avoid extensive machine learning models selection and optimizations, Automated Machine Learning (AutoML) has arisen as a practical and efficient way to apply machine learning to many different application areas. Data poisoning is a real threat to the accuracy of machine learning models in different settings, and it has in recent research studies been shown that the usage of AutoML can be even more sensitive to data poisoning than is the case for non-AutoML generated models. On the other hand, the usage of AutoML also has the potential of improving the robustness of a model by adapting the model to adversarial patterns. In this way, good accuracy can be maintained despite the attacker’s efforts to poison the data. However, no previous studies have investigated these effects. In this paper, we examine the risks associated with adversarial trajectory attacks in mobile systems, specifically looking into mobility prediction problems. By using mobility data from two different simulation frameworks: a simulator developed by Ericsson, which is based on a real-world deployment of Airtel’s open-network topology, and the ONE framework, we investigate three different AutoML frameworks and how the mobility accuracy for the frameworks is affected by a mobile trajectory attack. Our results show that re-running AutoML at every retraining is vulnerable to adversarial mobility poisoning and shows high accuracy variance. By contrast, using a single, well-chosen model from an initial AutoML search achieves more stable performance across adversarial conditions, even when the training set includes up to 10% adversarial mobility data.

Loading PDF

Similar Papers
  • Research Article
  • Citations8

Explainability Versus Accuracy of Machine Learning Models: The Role of Task Uncertainty and Need for Interaction with the Machine Learning Model

  • Feb 19, 2025
  • European Accounting Review
  • Dominik Hammann +1
  • Research Article

Una revisión sistemática de la literatura sobre la precisión de modelos de aprendizaje automático aplicados a la tasación de bienes raíces

  • Nov 01, 2024
  • Revista de Investigación en Tecnologías de la Información
  • Fabián Espinoza Garza +3
  • Research Article
  • Citations2

Improving Data Quality with Advanced Pre-Processing of MWD Data

  • Apr 30, 2025
  • Geotechnics
  • Alla Sapronova +1
  • PDF
  • Research Article
  • Citations20

Practical Considerations for Accuracy Evaluation in Sensor-Based Machine Learning and Deep Learning

  • Aug 09, 2019
  • Sensors (Basel, Switzerland)
  • Issam Hammad +1
  • Research Article

Optimization of machine learning model training procedure on multi-gpu systems to enhance cyber security in telecommunication networks

  • Sep 05, 2024
  • Scientific Bulletin of UNFU
  • O P Kuziv +1
  • PDF
  • Research Article
  • Citations9

Machine Learning Models to Predict Kidney Stone Recurrence Using 24 Hour Urine Testing and Electronic Health Record-Derived Features

  • Jun 29, 2023
  • Research Square
  • Patrick Doyle +3
  • PDF
  • Research Article
  • Citations16

Application of Machine Learning in Predicting Formation Condition of Multi-Gas Hydrate

  • Jun 28, 2022
  • Energies
  • Zimeng Yu +1
  • PDF
  • Research Article
  • Citations26

Artificial intelligence in the GPs office: a retrospective study on diagnostic accuracy

  • Sep 28, 2021
  • Scandinavian Journal of Primary Health Care
  • Steindor Ellertsson +2
  • Research Article
  • Citations79

Federated learning for 6G-enabled secure communication systems: a comprehensive survey

  • Mar 12, 2023
  • Artificial Intelligence Review
  • Deepika Sirohi +5
  • Supplementary Content
  • Citations17

Predicting radiation pneumonitis in lung cancer using machine learning and multimodal features: a systematic review and meta-analysis of diagnostic accuracy

  • Nov 05, 2024
  • BMC Cancer
  • Zhi Chen +8
  • Research Article
  • Citations21

Transfer Learning Facilitates the Prediction of Polymer-Surface Adhesion Strength.

  • Apr 17, 2023
  • Journal of Chemical Theory and Computation
  • Jiale Shi +4
  • Research Article
  • Citations3

Developing machine learning–based prognostic models for gestational choriocarcinoma: Insights into treatment efficacy and patient survival.

  • Jun 01, 2024
  • Journal of Clinical Oncology
  • Mustafa Alshwayyat +4
  • Conference Article
  • Citations4

Energy Cost and Machine Learning Accuracy Impact of k-Anonymisation and Synthetic Data Techniques

  • Jun 05, 2023
  • Pepijn De Reus +2
  • PDF
  • Research Article
  • Citations40

Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis.

  • Nov 20, 2023
  • JMIR Medical Informatics
  • Kui Liu +9
  • PDF
  • Research Article
  • Citations14

Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG)

  • Sep 29, 2023
  • Computers
  • Swetha Lenkala +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.