SMINT: Toward Interpretable and Robust Model Sharing for Deep Neural Networks

Huijun Wu
Huijun Wu
Chen Wang
Chen Wang
Richard Nock
Richard Nock

ACM Transactions on the Web, pp. 1-28, 2020.

Cited by: 0|Bibtex|Views46|DOI:https://doi.org/10.1145/3381833
EI
Other Links: dl.acm.org|dblp.uni-trier.de|academic.microsoft.com

Abstract:

Sharing a pre-trained machine learning model, particularly a deep neural network via prediction APIs, is becoming a common practice on machine learning as a service (MLaaS) platforms nowadays. Although deep neural networks (DNN) have shown remarkable successes in many tasks, they are also criticized for the lack of interpretability and tr...More

Code:

Data:

Your rating :
0

 

Tags
Comments