White-box Fairness Testing through Adversarial Sampling
Technical
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).
Tue 7 Jul Times are displayed in time zone: (UTC) Coordinated Universal Time change
08:05 - 09:05 | I5-Deep Learning Testing and DebuggingPaper Presentations / Technical Papers / Demonstrations at Goguryeo Chair(s): Pooyan JamshidiUniversity of South Carolina | ||
08:05 12mTalk | DISSECTOR: Input Validation for Deep Learning Applications by Crossing-layer DissectionTechnical Technical Papers Huiyan WangState Key Lab. for Novel Software Tech. and Dept. of Comp. Sci. and Tech., Nanjing University, Nanjing, China, Jingwei XuNanjing University, Chang XuNanjing University, Xiaoxing MaNanjing University, Jian LuNanjing University | ||
08:17 12mTalk | White-box Fairness Testing through Adversarial Sampling Technical Papers Peixin ZhangZhejiang University, Jingyi WangNational University of Singapore, Singapore, Jun SunSingapore Management University, Guoliang DongComputer College of Zhejiang University, Xinyu WangZhejiang University, Xingen WangZhejiang University, Jin Song DongNational University of Singapore, Dai TingHuawei Corporation | ||
08:29 3mTalk | FeatureNET: Diversity-driven Generation of Deep Learning ModelsDemo Demonstrations Salah GhamiziSntT - University of Luxembourg, Maxime CordySnT, University of Luxembourg, Mike PapadakisUniversity of Luxembourg, Yves Le TraonUniversity of Luxembourg | ||
08:32 3mTalk | EvalDNN: A Toolbox for Evaluating Deep Neural Network ModelsDemo Demonstrations Yongqiang TIANThe Hong Kong University of Science and Technology, Zhihua ZengZhejiang University, Ming WenHuazhong University of Science and Technology, China, Yepang LiuSouthern University of Science and Technology, Tzu-yang KuoThe Hong Kong University of Science and Technology, Shing-Chi CheungDepartment of Computer Science and Engineering, The Hong Kong University of Science and Technology | ||
08:35 12mTalk | Taxonomy of Real Faults in Deep Learning Systems Technical Papers Nargiz HumbatovaUniversità della Svizzera italiana, Gunel JahangirovaUniversità della Svizzera italiana, Gabriele BavotaUniversità della Svizzera italiana, Vincenzo RiccioUniversità della Svizzera italiana, Andrea StoccoUniversità della Svizzera italiana, Paolo TonellaUniversità della Svizzera italiana | ||
08:47 12mTalk | An Empirical Study on Program Failures of Deep Learning Jobs Technical Papers Ru ZhangMicrosoft Research, Wencong XiaoAlibaba, Hongyu ZhangUniversity of Newcastle, Australia, Yu LiuMicrosoft Research, Haoxiang LinMicrosoft Research, Mao YangMicrosoft Research | ||