# Adversarial Attacks on Probabilistic Autoregressive Forecasting Models

arXiv: https://arxiv.org/abs/2003.03778 · HTML: https://mlsanity.com/paper/2003.03778/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2020.

## Built on by (most cited first, 13 of 13)

- [BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting](https://mlsanity.com/paper/2410.02195/) (2024)
- [Adversarial robustness of amortized Bayesian inference](https://mlsanity.com/paper/2305.14984/) (2023)
- [Robust Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2202.11910/) (2022)
- [Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms](https://mlsanity.com/paper/2207.09572/) (2022)
- [Targeted Attacks on Timeseries Forecasting](https://mlsanity.com/paper/2301.11544/) (2023)
- [Adversarial News and Lost Profits: Manipulating Headlines in LLM-Driven Algorithmic Trading](https://mlsanity.com/paper/2601.13082/) (2026)
- [Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains](https://mlsanity.com/paper/2505.19397/) (2025)
- [Interpretability in Safety-Critical FinancialTrading Systems](https://mlsanity.com/paper/2109.15112/) (2021)
- [Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future](https://mlsanity.com/paper/2207.09912/) (2022)
- [INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression](https://mlsanity.com/paper/2604.11928/) (2026)
- [AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series Forecasting](https://mlsanity.com/paper/2310.19289/) (2023)
- [Manipulating hidden-Markov-model inferences by corrupting batch data](https://mlsanity.com/paper/2402.13287/) (2024)
- [Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting](https://mlsanity.com/paper/2512.12154/) (2025)

## Abstract (arXiv)

We develop an effective generation of adversarial attacks on neural models that output a sequence of probability distributions rather than a sequence of single values. This setting includes the recently proposed deep probabilistic autoregressive forecasting models that estimate the probability distribution of a time series given its past and achieve state-of-the-art results in a diverse set of application domains. The key technical challenge we address is effectively differentiating through the Monte-Carlo estimation of statistics of the joint distribution of the output sequence. Additionally, we extend prior work on probabilistic forecasting to the Bayesian setting which allows conditioning on future observations, instead of only on past observations. We demonstrate that our approach can successfully generate attacks with small input perturbations in two challenging tasks where robust decision making is crucial: stock market trading and prediction of electricity consumption.