Measuring and Comparing Robustness of ML Algorithms Under Adversarial Attack
CARNEGIE-MELLON UNIV PITTSBURGH PA PITTSBURGH United States
Pagination or Media Count:
A machine learning algorithm can be evaluated for robustness against any number of different types of attacks. We consider attacks that seek to manipulate the training andor testing data inputs to a machine learning algorithm. Specifically, we do not consider physical attacks on machines hosting the algorithm.
- Computer Programming and Software