A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Robust Feature Leakage

By Gabriel Goh. 2019

Subfields: Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

1. Aleksander Madry
2. Dimitris Tsipras
3. Logan Engstrom
4. Andrew Ilyas
5. Nicholas Carlini
6. Matthias Hein
7. Shibani Santurkar
8. Brandon Tran

Citations in the corpus

• Adversarial Examples Are Not Bugs, They Are Features (2019, background): “For instance, in principle, our theoretical framework would allow for useful non-robust features to arise as combinations of useful robust features and useless non-robust features [Goh19b].”