KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#developer-tools #typescript #claude-code #codex #dsh #dsh-plugin #ai-agent #ai-agents #deepseek-harness #agent-skills #macos #cli

InterpretationFragility

★ 38 Open GitHub ↗

Interpretation of Neural Network is Fragile

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# InterpretationFragility
Code for implementation of [Interpretation of Nueral Network is Fragile.](https://arxiv.org/pdf/1710.10547.pdf).

**Please cite the following work if you use this benchmark or the provided tools or implementations:**
```
@inproceedings{ghorbani2019interpretation,
  title={Interpretation of neural networks is fragile},
  author={Ghorbani, Amirata and Abid, Abubakar and Zou, James},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={33},
  pages={3681--3688},
  year={2019}
}
```
## Authors

* **Amirata Ghorbani** - [Website](http://web.stanford.edu/~amiratag)
* **Abubakar Abid** - [Website](https://abidlabs.github.io/)
* **James Zou** - [Website](https://sites.google.com/site/jamesyzou/)

## License

This project is licensed under the MIT License - see the [LICENSE.md](LICENSE.md) file for details

## The large scale results of attack methods against four famous feature-attribution methods
![alt text](https://github.com/amiratag/InterpretationFragility/blob/master/pictures/SaliencyMethodsComparison.png)

## Examples of targeted attack for semantically meaningful change in feature-importance
![alt text](https://github.com/amiratag/InterpretationFragility/blob/master/pictures/SemanticChange.png)

## Attack examples on Deep Taylor Decomposition
![alt text](https://github.com/amiratag/InterpretationFragility/blob/master/pictures/DTD_examples.png)

InterpretationFragility

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README