# The Dilemma Between Data Transformations and Adversarial Robustness for Time Series Application Systems

arXiv: https://arxiv.org/abs/2006.10885 · HTML: https://mlsanity.com/paper/2006.10885/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 6 of 6)

- [Projected Randomized Smoothing for Certified Adversarial Robustness](https://mlsanity.com/paper/2309.13794/) (2023)
- [Explaining the role of Intrinsic Dimensionality in Adversarial Training](https://mlsanity.com/paper/2405.17130/) (2024)
- [Adversarial Sample Detection Through Neural Network Transport Dynamics](https://mlsanity.com/paper/2306.04252/) (2023)
- [Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting](https://mlsanity.com/paper/2311.09790/) (2023)
- [Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility](https://mlsanity.com/paper/2410.06921/) (2024)
- [CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection](https://mlsanity.com/paper/2504.01882/) (2025)

## Abstract (arXiv)

Adversarial examples, or nearly indistinguishable inputs created by an attacker, significantly reduce machine learning accuracy. Theoretical evidence has shown that the high intrinsic dimensionality of datasets facilitates an adversary's ability to develop effective adversarial examples in classification models. Adjacently, the presentation of data to a learning model impacts its performance. For example, we have seen this through dimensionality reduction techniques used to aid with the generalization of features in machine learning applications. Thus, data transformation techniques go hand-in-hand with state-of-the-art learning models in decision-making applications such as intelligent medical or military systems. With this work, we explore how data transformations techniques such as feature selection, dimensionality reduction, or trend extraction techniques may impact an adversary's ability to create effective adversarial samples on a recurrent neural network. Specifically, we analyze it from the perspective of the data manifold and the presentation of its intrinsic features. Our evaluation empirically shows that feature selection and trend extraction techniques may increase the RNN's vulnerability. A data transformation technique reduces the vulnerability to adversarial examples only if it approximates the dataset's intrinsic dimension, minimizes codimension, and maintains higher manifold coverage.