Exploiting the relationship between Kendall’s rank correlation and cosine similarity for attribution protection
Model attributions are important in deep neural networks as they aid practitioners in understanding the models, but recent studies reveal that attributions can be easily perturbed by adding imperceptible noise to the input. The non-differentiable Kendall's rank correlation is a key performan...
Saved in:
Main Authors: | Wang, Fan, Kong, Adams Wai Kin |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/161935 https://nips.cc/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
An intelligent system to recommend appropriate correlations for vertical multiphase flow
by: Ruttapone Chanlongsawaitkul
Published: (2011) -
Pose- and Attribute-consistent Person Image Synthesis
by: XU, Cheng, et al.
Published: (2023) -
A generative A.I. technique for structure and texture transfer in furniture design
by: Gallega, Rgee Wharlo
Published: (2021) -
Exploiting future information for next point-of-interest recommendation
by: Peng, Jiao
Published: (2022) -
Exploring the similarities of XAI approaches in finding the influential factors in lung cancer survival rate
by: Tan, Elise Zining
Published: (2024)