mlsanityData to 14 Oct 2026

iADCPS: Time Series Anomaly Detection for Evolving Cyber-physical Systems via Incremental Meta-learning

arXiv 2504.04374 ↗First posted 6 Apr 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Anomaly detection for cyber-physical systems (ADCPS) is crucial in identifying faults and potential attacks by analyzing the time series of sensor measurements and actuator states. However, current methods lack adaptation to data distribution shifts in both temporal and spatial dimensions as cyber-physical systems evolve. To tackle this issue, we propose an incremental meta-learning-based approach, namely iADCPS, which can continuously update the model through limited evolving normal samples to reconcile the distribution gap between evolving and historical time series. Specifically, We first introduce a temporal mixup strategy to align data for data-level generalization which is then combined with the one-class meta-learning approach for model-level generalization. Furthermore, we develop a non-parametric dynamic threshold to adaptively adjust the threshold based on the probability density of the abnormal scores without any anomaly supervision. We empirically evaluate the effectiveness of the iADCPS using three publicly available datasets PUMP, SWaT, and WADI. The experimental results demonstrate that our method achieves 99.0%, 93.1%, and 78.7% F1-Score, respectively, which outperforms the state-of-the-art (SOTA) ADCPS method, especially in the context of the evolving CPSs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 52 references that are in the map. First posted on arXiv 6 Apr 2025.

Builds on

22 of 52 references.

References · 22

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  3. 2020A review on outlier/anomaly detection in time series datacited by 189
  4. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  5. 2020iTAML: An Incremental Task-Agnostic Meta-learning Approachcited by 90
  6. 2018Unsupervised Meta-Learning For Few-Shot Image Classificationcited by 75
  7. 2020Incremental Object Detection via Meta-Learningcited by 58
  8. 2020Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approachcited by 56
  9. 2021Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filteringcited by 31
  10. 2020Deep Learning-Based Anomaly Detection in Cyber-Physical Systems: Progress and Opportunitiescited by 27
  11. 2023DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecastingcited by 21
  12. 2017Anomaly Detection for a Water Treatment System Using Unsupervised Machine Learningcited by 18
10 more
  1. 2022Learning Deep Time-index Models for Time Series Forecastingcited by 18
  2. 2022Contrastive Domain Adaptation for Time-Series via Temporal Mixupcited by 18
  3. 2020Few-Shot One-Class Classification via Meta-Learningcited by 17
  4. 2020Real-World Anomaly Detection by using Digital Twin Systems and Weakly-Supervised Learningcited by 17
  5. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  6. 2022Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Streamcited by 13
  7. 2021Cybersecurity of Industrial Cyber-Physical Systems: A Reviewcited by 10
  8. 2023Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systemscited by 6
  9. 2023MTS-DVGAN: Anomaly Detection in Cyber-Physical Systems using a Dual Variational Generative Adversarial Networkcited by 5
  10. 2018Checking is Believing: Event-Aware Program Anomaly Detection in Cyber-Physical Systemscited by 2

Built on by

Not cited yet.