Automatic fairness testing of neural classifiers through adversarial sampling

• Main Authors: ZHANG, Peixin, WANG, Jingyi, SUN, Jun, WANG, Xinyu, DONG, Guoliang, WANG, Xinggen, DAI, Ting, DONG, Jinsong
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2021
• 主題: Deep learning; fairness testing; individual discrimination; gradient; Software Engineering
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/6224; https://ink.library.smu.edu.sg/context/sis_research/article/7227/viewcontent/09506918.pdf

Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e., non-discrimination). Unfortunately, discrimination might be intrinsical...