adversarial-explainable-ai icon indicating copy to clipboard operation
adversarial-explainable-ai copied to clipboard

Published 20 hours ago • verified publisher icon hbaniecki

Brittle interpretations: The Vulnerability of TCAV and Other Concept-based Explainability Tools to Adversarial Attack

Open hbaniecki opened this issue 3 years ago • 0 comments

https://openreview.net/forum?id=a3hQPNqIFk6

hbaniecki avatar Oct 11 '21 05:10 hbaniecki