Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
10-2020
Abstract
Although deep neural networks (DNNs) have demonstrated astonishing performance in many applications, there are still concerns on their dependability. One desirable property of DNN for applications with societal impact is fairness (i.e., non-discrimination). In this work, we propose a scalable approach for searching individual discriminatory instances of DNN. Compared with state-of-the-art methods, our approach only employs lightweight procedures like gradient computation and clustering, which makes it significantly more scalable than existing methods. Experimental results show that our approach explores the search space more effectively (9 times) and generates much more individual discriminatory instances (25 times) using much less time (half to 1/7) .
Discipline
Information Security | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
ICSE '20: Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering, Seoul, October 5-11
First Page
949
Last Page
960
ISBN
9781450371216
Identifier
10.1145/3377811.3380331
Publisher
ACM
City or Country
New York
Citation
ZHANG, Peixin; WANG, Jingyi; SUN, Jun; DONG, Guoliang; WANG, Xinyu; WANG, Xingen; DONG, Jin Song; and TING, Dai.
White-box fairness testing through adversarial sampling. (2020). ICSE '20: Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering, Seoul, October 5-11. 949-960.
Available at: https://ink.library.smu.edu.sg/sis_research/4632
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1145/3377811.3380331