mlsanityData to 7 Oct 2026

BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting

arXiv 2410.02195 ↗First posted 3 Oct 2024cs.LG cs.AI cs.CRcited by 18

Not on the map. Why?

Abstract (arXiv)

Multivariate Time Series (MTS) forecasting is a fundamental task with numerous real-world applications, such as transportation, climate, and epidemiology. While a myriad of powerful deep learning models have been developed for this task, few works have explored the robustness of MTS forecasting models to malicious attacks, which is crucial for their trustworthy employment in high-stake scenarios. To address this gap, we dive deep into the backdoor attacks on MTS forecasting models and propose an effective attack method named BackTime.By subtly injecting a few stealthy triggers into the MTS data, BackTime can alter the predictions of the forecasting model according to the attacker's intent. Specifically, BackTime first identifies vulnerable timestamps in the data for poisoning, and then adaptively synthesizes stealthy and effective triggers by solving a bi-level optimization problem with a GNN-based trigger generator. Extensive experiments across multiple datasets and state-of-the-art MTS forecasting models demonstrate the effectiveness, versatility, and stealthiness of method attacks. The code is available at urlhttps://github.com/xiaolin-cs/BackTime.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 35 of its 84 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

35 of 84 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  7. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  8. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  10. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  11. 2018Spectral Signatures in Backdoor Attackscited by 457
  12. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
23 more
  1. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 385
  2. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  3. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  4. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 267
  5. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  6. 2019A backdoor attack against LSTM-based text classification systemscited by 214
  7. 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 209
  8. 2019Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directionscited by 172
  9. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 162
  10. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  11. 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 141
  12. 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 131
  13. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 43
  14. 2024VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connectionscited by 34
  15. 2021Network of Tensor Time Seriescited by 32
  16. 2017Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networkscited by 28
  17. 2020Adversarial Examples in Deep Learning for Multivariate Time Series Regressioncited by 26
  18. 2023Graph Neural Banditscited by 20
  19. 2020Adversarial Attacks on Probabilistic Autoregressive Forecasting Modelscited by 13
  20. 2023BeMap: Balanced Message Passing for Fair Graph Neural Networkcited by 11
  21. 2022Backdoor Attacks on Time Series: A Generative Approachcited by 10
  22. 2024Generating Fine-Grained Causality in Climate Time Series Data for Forecasting and Anomaly Detectioncited by 7
  23. 2024On the Generalization Capability of Temporal Graph Learning Algorithms: Theoretical Insights and a Simpler Methodcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 7.

18 papers.

Sort:

By area:

  1. 2025Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrativecited by 35
  2. 2025Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesicscited by 17
  3. 2024PageRank Bandits for Link Predictioncited by 14
  4. 2025Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecastingcited by 12
  5. 2024Ask, and it shall be given: On the Turing completeness of promptingcited by 10
  6. 2025Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problemcited by 5
  7. 2025Learnable Spatial-Temporal Positional Encoding for Link Predictioncited by 3
  8. 2025Trojan Horse Hunt in Time Series Forecasting for Space Operationscited by 2
  9. 2025Continual Low-Rank Adapters for LLM-based Generative Recommender Systemscited by 2
  10. 2025Saffron-1: Safety Inference Scalingcited by 1
  11. 2026OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detectioncited by 1
  12. 2026Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learningcited by 1
6 more
  1. 2026ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuningcited by 1
  2. 2026AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspectivecited by 1
  3. 2026Adversarial Robustness of Deep State Space Models for Forecastingcited by 1
  4. 2025Connecting Domains and Contrasting Samples: A Ladder for Domain Generalizationcited by 0
  5. 2026TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecastingcited by 0
  6. 2026Structuring and Tokenizing Distributed User Interest Context for Generative Recommendationcited by 0