Search Results for author:
Found 2 papers, 0 papers with code
Where Classification Fails, Interpretation Rises
We believe that this work opens a new direction for designing adversarial input detection methods.
Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results
On the possibility side, we show that it is still feasible to construct adversarial training methods to significantly improve the resilience of networks against adversarial inputs over empirical datasets.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
