Summary of Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots, by Xi Xin et al.
Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots
by Xi Xin, Giles Hooker, Fei Huang
First submitted to arxiv on: 29 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Applications (stat.AP); Machine Learning (stat.ML)
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 The proposed adversarial framework manipulates machine learning models to produce deceptive partial dependence (PD) plots, concealing discriminatory behaviors in auto insurance claims and COMPAS datasets while maintaining most predictions. This technique creates multiple fooled PD plots using a single model. By applying this framework to real-world data, the paper demonstrates the vulnerability of permutation-based interpretation methods for decision-making. Managerial insights are provided for regulators and practitioners. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper shows how artificial intelligence models can be tricked into hiding discriminatory behavior in auto insurance claims and a system that predicts prison sentences. The authors created a new way to manipulate these complex models, making them appear fair when they’re not. This is important because AI is used more and more in decisions about people’s lives, so it’s crucial to make sure these models are honest. |
Keywords
» Artificial intelligence » Machine learning
