A review and benchmark of feature importance methods for neural networks
H Mandler, B Weigand - ACM Computing Surveys, 2024 - dl.acm.org
Feature attribution methods (AMs) are a simple means to provide explanations for the
predictions of black-box models such as neural networks. Due to their conceptual …
predictions of black-box models such as neural networks. Due to their conceptual …
Bayesian Networks for Interpretable Cyberattack Detection
B Yang, M Hoffman, N Brown - 2023 - scholarspace.manoa.hawaii.edu
The challenge of cyberattack detection can be illustrated by the complexity of the MITRE
ATT&CKTM matrix, which catalogues> 200 attack techniques (most with multiple sub …
ATT&CKTM matrix, which catalogues> 200 attack techniques (most with multiple sub …
[PDF][PDF] A Bayesian Network Pipeline for Detection of Cyberattacks.
N Brown, M Hoffman, B Yang - 2022 - osti.gov
MLDL 2022: A Bayesian Network Pipeline for Detection of Cyberattacks Nathanael Brown (5521)
Page 1 SAND2022-XXXX MLDL 2022: A Bayesian Network Pipeline for Detection of …
Page 1 SAND2022-XXXX MLDL 2022: A Bayesian Network Pipeline for Detection of …