Marble: Model-based robustness analysis of stateful deep learning systems
State-of-the-art deep learning (DL) systems are vulnerable to adversarial examples, which hinders their potential adoption in safetyand security-critical scenarios. While some recent progress has been made in analyzing the robustness of feed-forward neural networks, the robustness analysis for state...
Saved in:
Main Authors: | DU, Xiaoning, LI, Yi, XIE, Xiaofei, MA, Lei, LIU, Yang, ZHAO, Jianjun |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2020
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7088 https://ink.library.smu.edu.sg/context/sis_research/article/8091/viewcontent/3324884.3416564.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
DeepStellar: Model-based quantitative analysis of stateful deep learning systems
by: DU, Xiaoning, et al.
Published: (2019) -
DeepMutation++: A mutation testing framework for deep learning systems
by: HU, Qiang, et al.
Published: (2019) -
A quantitative analysis framework for recurrent neural network
by: DU, Xiaoning, et al.
Published: (2019) -
Towards characterizing adversarial defects of deep learning software from the lens of uncertainty
by: ZHANG, Xiyue, et al.
Published: (2020) -
DeepHunter: A coverage-guided fuzz testing framework for deep neural networks
by: XIE, Xiaofei, et al.
Published: (2019)