Affected by the COVID 2019, ICSE 2020 (the 42nd International Conference on Software Engineering) that originally scheduled to be held in Seoul, Korea from May 23 to May 29, was changed to be held online from July 6 to July 11. A total of 10 papers from the College of Computer Science and Technology, Zhejiang University were accepted. Among them, the paper, White-box Fairness Testing through Adversarial Sampling, from Prof. Xinyu Wang’s research team was awarded the ACM SIGSOFT Distinguished paper. This is the 2nd time the team has obtained this honor in recent three years.
ICSE is recognized as the top conference in the field of software engineering. Many researchers from all over the world submit and participate in the conference every year. According to the organizer, ICSE 2020 received a total of 621 paper submissions from around the world. After strict reviewing, 129 papers were accepted, and 10 distinguished papers were selected. The paper from Prof. Xinyu Wang’s team was selected as outstanding papers. The first author of this paper is the PhD student Peixin Zhang of this team, and the main co-authors include his supervisor, Prof. Xinyu Wang from Zhejiang University, and his co-supervisor, Prof. Sun Jun from Singapore Management University.
Research Overview
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). This work proposes a scalable approach for searching individual discriminatory instances of DNN. Compared with state-of-the art methods, the approach only employs lightweight procedures like gradient computation and clustering, which makes it significantly more scalable than existing methods. Experimental results show that the 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).
The software engineering team of the College of Computer Science, Zhejiang University has achieved world-class research results in software analysis, software library mining, empirical software engineering and artificial intelligence testing and analysis. In recent years, the team has published more than 40 papers in CCF A journals and conferences in the field of software engineering, and won CCF A Conference Distinguished Paper Award for four times. Based on tripartite university-industry-research cooperation, the software engineering team has built an efficient talent training, scientific research cooperation and industry incubation mechanism. The scientific research cooperation with Singapore Management University, Singapore University of Technology and Design, Monash University in Australia, UBC in Canada and other universities have achieved remarkable results. The industrial cooperation with State Street Corp, Hengtian Software, Bangsheng Technology, Hyperchain Technology, HarmonyCloud Technology and other enterprises have also come into fruition, which exerts a positive impact on China’s software industry and the global open source community.
（From: College of Computer Science and Technology)