# The Search for Sparse, Robust Neural Networks

arXiv: https://arxiv.org/abs/1912.02386 · HTML: https://mlsanity.com/paper/1912.02386/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2019.

## Built on by (most cited first, 11 of 11)

- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [GANs Can Play Lottery Tickets Too](https://mlsanity.com/paper/2106.00134/) (2021)
- [Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness](https://mlsanity.com/paper/2409.01249/) (2024)
- [Machine Learning Robustness: A Primer](https://mlsanity.com/paper/2404.00897/) (2024)
- [Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2508.06871/) (2025)
- [Finding Dynamics Preserving Adversarial Winning Tickets](https://mlsanity.com/paper/2202.06488/) (2022)
- [Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks](https://mlsanity.com/paper/2503.20454/) (2025)
- [Spatio-Temporal Sparsification for General Robust Graph Convolution Networks](https://mlsanity.com/paper/2103.12256/) (2021)
- [One is More: Diverse Perspectives within a Single Network for Efficient DRL](https://mlsanity.com/paper/2310.14009/) (2023)
- [Chasing Better Deep Image Priors between Over- and Under-parameterization](https://mlsanity.com/paper/2410.24187/) (2024)
- [Pruning Cannot Hurt Robustness: Certified Trade-offs in Reinforcement Learning](https://mlsanity.com/paper/2510.12939/) (2025)

## Abstract (arXiv)

Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to pruning literature, deep neural networks are known to be susceptible to adversarial examples, which may pose risks in security- or safety-critical applications. Intuition suggests that there is an inherent trade-off between sparsity and robustness such that these characteristics could not co-exist. We perform an extensive empirical evaluation and analysis testing the Lottery Ticket Hypothesis with adversarial training and show this approach enables us to find sparse, robust neural networks. Code for reproducing experiments is available here: https://github.com/justincosentino/robust-sparse-networks.