Summary of Adversarial Pruning: a Survey and Benchmark Of Pruning Methods For Adversarial Robustness, by Giorgio Piras et al.
Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
by Giorgio Piras, Maura Pintor, Ambra Demontis, Battista Biggio, Giorgio Giacinto, Fabio Roli
First submitted to arxiv on: 2 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper surveys current neural network pruning techniques designed to reduce model size while preserving robustness against adversarial examples. The authors propose a novel taxonomy to categorize these methods based on the pipeline and specifics of pruning, overcoming complexities that hinder fair comparison. They also highlight limitations in existing empirical analyses and introduce a new evaluation benchmark to address them. An empirical re-evaluation of current adversarial pruning methods reveals shared traits among top-performing approaches and common issues. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at ways to make neural networks smaller while keeping them good at recognizing fake examples. It groups these techniques into categories based on when and how they work. The authors also point out problems with how people have tested these methods in the past and suggest a new way to test them that is fairer. They then re-test all the current methods using this new benchmark, which shows what makes some methods better than others. |
Keywords
» Artificial intelligence » Neural network » Pruning
