Revisiting neuron coverage metrics and quality of deep neural networks
Deep neural networks (DNN) have been widely applied in modern life, including critical domains like autonomous driving, making it essential to ensure the reliability and robustness of DNN-powered systems. As an analogy to code coverage metrics for testing conventional software, researchers have prop...
Saved in:
Main Authors: | YANG, Zhou, SHI, Jieke, ASYROFI, Muhammad Hilmi, LO, David |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7625 https://ink.library.smu.edu.sg/context/sis_research/article/8628/viewcontent/378600a408.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
NPC: Neuron path coverage via characterizing decision logic of deep neural networks
by: XIE, Xiaofei, et al.
Published: (2022) -
NPC: neuron path coverage via characterizing decision logic of deep neural networks
by: Xie, Xiaofei, et al.
Published: (2022) -
Seed selection for testing deep neural networks
by: ZHI, Yuhan, et al.
Published: (2023) -
Deep learning for coverage-guided fuzzing: How far are we?
by: LI, Siqi, et al.
Published: (2022) -
KAPE: kNN-based performance testing for deep code search
by: GUO, Yuejun, et al.
Published: (2023)