mlsanityData to 7 Oct 2026

Adversarial Attacks on Time Series

arXiv 1902.10755 ↗First posted 27 Feb 2019cs.LG stat.MLcited by 40

Not on the map. Why?

Abstract (arXiv)

Time series classification models have been garnering significant importance in the research community. However, not much research has been done on generating adversarial samples for these models. These adversarial samples can become a security concern. In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical time series classification models. Our proposed methodology is applied onto 1-Nearest Neighbor Dynamic Time Warping (1-NN ) DTW, a Fully Connected Network and a Fully Convolutional Network (FCN), all of which are trained on 42 University of California Riverside (UCR) datasets. In this paper, we show both models were susceptible to attacks on all 42 datasets. To the best of our knowledge, such an attack on time series classification models has never been done before. Finally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples and to consider model robustness as an evaluative metric.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 9; 2023: 9; 2024: 5; 2025: 6; 2026: 6.

40 papers.

Sort:

By area:

  1. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  2. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  3. 2021Are socially-aware trajectory prediction models really socially-aware?cited by 32
  4. 2021BASAR:Black-box Attack on Skeletal Action Recognitioncited by 25
  5. 2021Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attackcited by 23
  6. 2024Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysiscited by 16
  7. 2022Robust Probabilistic Time Series Forecastingcited by 15
  8. 2022TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attackcited by 9
  9. 2023Targeted Adversarial Attacks on Wind Power Forecastscited by 9
  10. 2022Defending Black-box Skeleton-based Human Activity Classifierscited by 8
  11. 2023Targeted Attacks on Timeseries Forecastingcited by 8
  12. 2021Adversarial Attacks and Defenses in Physiological Computing: A Systematic Reviewcited by 7
28 more
  1. 2022Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Featurescited by 7
  2. 2022Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attackcited by 7
  3. 2023SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Seriescited by 6
  4. 2022Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerabilitycited by 5
  5. 2025Unifying Prediction and Explanation in Time-Series Transformers via Shapley-based Pretrainingcited by 5
  6. 2021Spatially Focused Attack against Spatiotemporal Graph Neural Networkscited by 4
  7. 2022Dynamic Time Warping based Adversarial Framework for Time-Series Domaincited by 4
  8. 2022Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challengescited by 3
  9. 2024Adversarial Attacks and Defenses in Multivariate Time-Series Forecasting for Smart and Connected Infrastructurescited by 3
  10. 2025Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domainscited by 2
  11. 2022Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysiscited by 1
  12. 2023Post-train Black-box Defense via Bayesian Boundary Correctioncited by 1
  13. 2023Not So Robust After All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attackscited by 1
  14. 2023Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecastingcited by 1
  15. 2025Concealed Adversarial attacks on neural networks for sequential datacited by 1
  16. 2025Mini-Batch Robustness Verification of Deep Neural Networkscited by 1
  17. 2023Wasserstein Adversarial Examples on Univariant Time Series Datacited by 0
  18. 2024Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Featurescited by 0
  19. 2024Correlation Analysis of Adversarial Attack in Time Series Classificationcited by 0
  20. 2024Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemblecited by 0
  21. 2025Differentiable Adversarial Attacks for Marked Temporal Point Processescited by 0
  22. 2025Adversarial VR: An Open-Source Testbed for Evaluating Adversarial Robustness of VR Cybersickness Detection and Mitigationcited by 0
  23. 2026Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attackscited by 0
  24. 2026Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attackscited by 0
  25. 2026Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognitioncited by 0
  26. 2026Adversarial Attacks on Online Handwriting using Salience-based Temporal Editingcited by 0
  27. 2026GENADA: efficient generative time series adversarial attack frameworkcited by 0
  28. 2026LogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systemscited by 0