Summary of Fooling Shap with Output Shuffling Attacks, by Jun Yuan et al.
Fooling SHAP with Output Shuffling Attacks
by Jun Yuan, Aritra Dasgupta
First submitted to arxiv on: 12 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
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 proposes novel data-agnostic adversarial attacks called shuffling attacks that subvert explainable AI (XAI) methods, particularly SHAP. These attacks can adapt any trained machine learning model to fool Shapley value-based explanations. The proposed attack strategies are shown to be undetectable by Shapley values but can be detected with varying degrees of effectiveness by algorithms that estimate Shapley values like linear SHAP and SHAP. The paper demonstrates the efficacy of these attacks using real-world datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research looks at ways to make AI “cheat” or give wrong answers. They want to see if a special kind of AI explanation tool can be tricked into saying something is fair when it’s not. The researchers came up with new ways to do this that don’t need access to the original data. They tested these tricks on real-world datasets and found they work. |
Keywords
» Artificial intelligence » Machine learning
