# Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Series

arXiv: https://arxiv.org/abs/2101.05639 · HTML: https://mlsanity.com/paper/2101.05639/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 13 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks](https://mlsanity.com/paper/1904.00887/) (2019)
- [Adversarial Attacks on Deep Neural Networks for Time Series Classification](https://mlsanity.com/paper/1903.07054/) (2019)
- [On Accurate and Reliable Anomaly Detection for Gas Turbine Combustors: A Deep Learning Approach](https://mlsanity.com/paper/1908.09238/) (2019)
- [Universal, transferable and targeted adversarial attacks](https://mlsanity.com/paper/1908.11332/) (2019)

## Built on by (most cited first, 21 of 21)

- [A Survey on Time-Series Pre-Trained Models](https://mlsanity.com/paper/2305.10716/) (2023)
- [Targeted Adversarial Attacks on Wind Power Forecasts](https://mlsanity.com/paper/2303.16633/) (2023)
- [Targeted Attacks on Timeseries Forecasting](https://mlsanity.com/paper/2301.11544/) (2023)
- [SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series](https://mlsanity.com/paper/2309.02752/) (2023)
- [Competence-Based Analysis of Language Models](https://mlsanity.com/paper/2303.00333/) (2023)
- [Universal Adversarial Attack on Deep Learning Based Prognostics](https://mlsanity.com/paper/2109.07142/) (2021)
- [On the Susceptibility and Robustness of Time Series Models through Adversarial Attack and Defense](https://mlsanity.com/paper/2301.03703/) (2023)
- [Efficient Black-Box Adversarial Attacks on Neural Text Detectors](https://mlsanity.com/paper/2311.01873/) (2023)
- [Adversarial Attacks and Defenses in Multivariate Time-Series Forecasting for Smart and Connected Infrastructures](https://mlsanity.com/paper/2408.14875/) (2024)
- [Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization](https://mlsanity.com/paper/2311.13656/) (2023)
- [FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks](https://mlsanity.com/paper/2312.04587/) (2023)
- [New Paradigm of Adversarial Training: Releasing Accuracy-Robustness Trade-Off via Dummy Class](https://mlsanity.com/paper/2410.12671/) (2024)
- [Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains](https://mlsanity.com/paper/2505.19397/) (2025)
- [An Adaptive Black-box Backdoor Detection Method for Deep Neural Networks](https://mlsanity.com/paper/2204.04329/) (2022)
- [Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models](https://mlsanity.com/paper/2512.08832/) (2025)
- [LOGSAFE: Logic-Guided Verification for Trustworthy Federated Time-Series Learning](https://mlsanity.com/paper/2411.03231/) (2024)
- [Creating a Causally Grounded Rating Method for Assessing the Robustness of AI Models for Time-Series Forecasting](https://mlsanity.com/paper/2502.12226/) (2025)
- [Lightweight Defense Against Adversarial Attacks in Time Series Classification](https://mlsanity.com/paper/2505.02073/) (2025)
- [Targeted Manipulation: Slope-Based Attacks on Financial Time-Series Data](https://mlsanity.com/paper/2511.19330/) (2025)
- [Adversarial Attacks on Online Handwriting using Salience-based Temporal Editing](https://mlsanity.com/paper/2607.12500/) (2026)
- [When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers](https://mlsanity.com/paper/2609.29937/) (2026)

## Abstract (arXiv)

Deep learning based models are vulnerable to adversarial attacks. These attacks can be much more harmful in case of targeted attacks, where an attacker tries not only to fool the deep learning model, but also to misguide the model to predict a specific class. Such targeted and untargeted attacks are specifically tailored for an individual sample and require addition of an imperceptible noise to the sample. In contrast, universal adversarial attack calculates a special imperceptible noise which can be added to any sample of the given dataset so that, the deep learning model is forced to predict a wrong class. To the best of our knowledge these targeted and universal attacks on time series data have not been studied in any of the previous works. In this work, we have performed untargeted, targeted and universal adversarial attacks on UCR time series datasets. Our results show that deep learning based time series classification models are vulnerable to these attacks. We also show that universal adversarial attacks have good generalization property as it need only a fraction of the training data. We have also performed adversarial training based adversarial defense. Our results show that models trained adversarially using Fast gradient sign method (FGSM), a single step attack, are able to defend against FGSM as well as Basic iterative method (BIM), a popular iterative attack.