/InterpretationFragility

Interpretation of Neural Network is Fragile

Primary LanguageJupyter NotebookMIT LicenseMIT

Interpretation of Neural Network is Fragile

Please cite the following work if you use this benchmark or the provided tools or implementations:

[1] Amirata Ghorbani, Abubakar Abid, James Zou
    Interpretation of Neural Network is Fragile
    arXiv:1710.10547

The large scale results of attack methods against four famous feature-attribution methods

alt text

Examples of targeted attack for semantically meaningful change in feature-importance

alt text

Attack examples on Deep Taylor Decomposition

alt text