mlsanityData to 14 Oct 2026

Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting

arXiv 2412.08099 ↗First posted 11 Dec 2024cs.LG cs.AI cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have recently demonstrated significant potential in time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world applications remain under-explored, particularly concerning their susceptibility to adversarial attacks. In this paper, we introduce a targeted adversarial attack framework for LLM-based time series forecasting. By employing both gradient-free and black-box optimization methods, we generate minimal yet highly effective perturbations that significantly degrade the forecasting accuracy across multiple datasets and LLM architectures. Our experiments, which include models like LLMTime with GPT-3.5, GPT-4, LLaMa, and Mistral, TimeGPT, and TimeLLM show that adversarial attacks lead to much more severe performance degradation than random noise, and demonstrate the broad effectiveness of our attacks across different LLMs. The results underscore the critical vulnerabilities of LLMs in time series forecasting, highlighting the need for robust defense mechanisms to ensure their reliable deployment in practical applications. The code repository can be found at https://github.com/JohnsonJiang1996/AdvAttack_LLM4TS.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 41 references that are in the map. First posted on arXiv 11 Dec 2024.

Builds on

33 of 41 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  8. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  9. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  10. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  11. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  12. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
21 more
  1. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  2. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  3. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  4. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  5. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  6. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
  7. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 234
  8. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 168
  9. 2023TimeGPT-1cited by 158
  10. 2024Automatic and Universal Prompt Injection Attacks against Large Language Modelscited by 119
  11. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 110
  12. 2018Transferable Adversarial Attacks for Image and Video Object Detectioncited by 109
  13. 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Spacecited by 91
  14. 2024Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Modelscited by 86
  15. 2024Empowering Time Series Analysis with Large Language Models: A Surveycited by 60
  16. 2024PAL: Proxy-Guided Black-Box Attack on Large Language Modelscited by 50
  17. 2023TrojLLM: A Black-box Trojan Prompt Attack on Large Language Modelscited by 31
  18. 2022Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Modelscited by 29
  19. 2024Robustness of Large Language Models to Perturbations in Textcited by 11
  20. 2022Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanismscited by 8
  21. 2021Spatially Focused Attack against Spatiotemporal Graph Neural Networkscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Modelscited by 4
  2. 2025Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domainscited by 2
  3. 2026Adversarial Robustness of Deep State Space Models for Forecastingcited by 1
  4. 2025Error Adjustment Based on Spatiotemporal Correlation Fusion for Traffic Forecastingcited by 0
  5. 2026TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecastingcited by 0
  6. 2026The Corroboration Illusion: When More News Makes LLM Forecasts Less Truecited by 0