# Concealed Adversarial attacks on neural networks for sequential data

arXiv: https://arxiv.org/abs/2502.20948 · HTML: https://mlsanity.com/paper/2502.20948/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Bake off redux: a review and experimental evaluation of recent time series classification algorithms](https://mlsanity.com/paper/2304.13029/) (2023)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [Adversarial Attacks on Deep Neural Networks for Time Series Classification](https://mlsanity.com/paper/1903.07054/) (2019)
- [Fast and Accurate Time Series Classification with WEASEL](https://mlsanity.com/paper/1701.07681/) (2017)
- [Adversarial Attacks on Time Series](https://mlsanity.com/paper/1902.10755/) (2019)
- [Deep learning models for price forecasting of financial time series: A review of recent advancements: 2020-2022](https://mlsanity.com/paper/2305.04811/) (2023)
- [Adversarial Attacks on Multivariate Time Series](https://mlsanity.com/paper/2004.00410/) (2020)
- [Understanding Robustness of Visual State Space Models for Image Classification](https://mlsanity.com/paper/2403.10935/) (2024)
- [TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack](https://mlsanity.com/paper/2209.06388/) (2022)
- [Thresholded Lexicographic Ordered Multiobjective Reinforcement Learning](https://mlsanity.com/paper/2408.13493/) (2024)
- [Non-contrastive representation learning for intervals from well logs](https://mlsanity.com/paper/2209.14750/) (2022)
- [Towards Evaluating the Robustness of Visual State Space Models](https://mlsanity.com/paper/2406.09407/) (2024)

## Built on by (most cited first, 1 of 1)

- [GENADA: efficient generative time series adversarial attack framework](https://mlsanity.com/paper/2608.12535/) (2026)

## Abstract (arXiv)

The emergence of deep learning led to the broad usage of neural networks in the time series domain for various applications, including finance and medicine. While powerful, these models are prone to adversarial attacks: a benign targeted perturbation of input data leads to significant changes in a classifier's output. However, formally small attacks in the time series domain become easily detected by the human eye or a simple detector model. We develop a concealed adversarial attack for different time-series models: it provides more realistic perturbations, being hard to detect by a human or model discriminator. To achieve this goal, the proposed adversarial attack maximizes an aggregation of a classifier and a trained discriminator loss. To make the attack stronger, we also propose a training procedure for a discriminator that provides broader coverage of possible attacks. Extensive benchmarking on six UCR time series datasets across four diverse architectures - including recurrent, convolutional, state-space, and transformer-based models - demonstrates the superiority of our attack for a concealability-efficiency trade-off. Our findings highlight the growing challenge of designing robust time series models, emphasizing the need for improved defenses against realistic and effective attacks.