# Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks

arXiv: https://arxiv.org/abs/2310.08073 · HTML: https://mlsanity.com/paper/2310.08073/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 20 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 18 of 18)

- [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)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack](https://mlsanity.com/paper/1907.02044/) (2019)
- [What Do Compressed Deep Neural Networks Forget?](https://mlsanity.com/paper/1911.05248/) (2019)
- [Adversarial Robustness vs Model Compression, or Both?](https://mlsanity.com/paper/1903.12561/) (2019)
- [Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning](https://mlsanity.com/paper/1912.08881/) (2019)
- [Model Compression with Adversarial Robustness: A Unified Optimization Framework](https://mlsanity.com/paper/1902.03538/) (2019)
- [Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy](https://mlsanity.com/paper/2103.03014/) (2021)
- [Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints](https://mlsanity.com/paper/2102.12827/) (2021)
- [Pruning has a disparate impact on model accuracy](https://mlsanity.com/paper/2205.13574/) (2022)
- [Towards Compact and Robust Deep Neural Networks](https://mlsanity.com/paper/1906.06110/) (2019)

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

- [Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness](https://mlsanity.com/paper/2409.01249/) (2024)

## Abstract (arXiv)

Neural network pruning has shown to be an effective technique for reducing the network size, trading desirable properties like generalization and robustness to adversarial attacks for higher sparsity. Recent work has claimed that adversarial pruning methods can produce sparse networks while also preserving robustness to adversarial examples. In this work, we first re-evaluate three state-of-the-art adversarial pruning methods, showing that their robustness was indeed overestimated. We then compare pruned and dense versions of the same models, discovering that samples on thin ice, i.e., closer to the unpruned model's decision boundary, are typically misclassified after pruning. We conclude by discussing how this intuition may lead to designing more effective adversarial pruning methods in future work.