Summary of Deep Generative Models As An Adversarial Attack Strategy For Tabular Machine Learning, by Salijona Dyrmishi et al.
Deep generative models as an adversarial attack strategy for tabular machine learning
by Salijona Dyrmishi, Mihaela Cătălina Stoian, Eleonora Giunchiglia, Maxime Cordy
First submitted to arxiv on: 19 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 Deep Generative Models have been applied in computer vision to generate adversarial examples for testing machine learning systems’ robustness. However, extending these techniques to tabular machine learning poses unique challenges due to the nature of tabular data and the need to preserve domain constraints in adversarial examples. The paper adapts four popular tabular DGMs into adversarial DGMs (AdvDGMs) and evaluates their effectiveness in generating realistic adversarial examples that conform to domain constraints. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to trick a machine learning system by creating fake data that looks real. This is hard when working with numbers and tables, because the data has to make sense within its own rules. In this paper, scientists take four powerful tools used in computer vision for generating fake images and adapt them to work with tabular data. They then test these adapted tools to see how well they can create realistic fake data that follows the same rules as the real data. |
Keywords
* Artificial intelligence * Machine learning
