Write a Blog >>
ICSE 2020
Wed 24 June - Thu 16 July 2020
Wed 8 Jul 2020 02:10 - 03:00 at SRC Poster Special Room - P305-SRC-Posters

Deep learning (DL) systems, though being widely used, still suffer from quality and reliability issues. Researchers have put many efforts to investigate these issues. One promising direction is to leverage uncertainty, an intrinsic characteristic of DL systems when making decisions, to better understand their erroneous behavior. DL system testing is an effective method to reveal potential defects before the deployment into safety- and security-critical applications. Various techniques and criteria have been designed to generate defect-triggers, i.e. adversarial examples (AEs). However, whether these test inputs could achieve a full spectrum examination of DL systems remains unknown and there still lacks understanding of the relation between AEs and DL uncertainty. In this work, we first conduct an empirical study to uncover the characteristics of AEs from the perspective of uncertainty. Then, we propose a novel approach to generate unique inputs that are missed by existing techniques. The generated data are demonstrated to be more effective in revealing defects even for DL systems equipped with defense mechanism. Further, we investigate the usefulness and effectiveness of the data for DL robustness enhancement.

Wed 8 Jul
Times are displayed in time zone: (UTC) Coordinated Universal Time change

02:10 - 03:00
Poster
ACM Student Research Competition
Yiwen WuNational University of Defense Technology
02:10 - 03:00
Poster
ACM Student Research Competition
Xiufeng XuPeking University
02:10 - 03:00
Poster
ACM Student Research Competition
Chengyu ZhangEast China Normal University
02:10 - 03:00
Poster
ACM Student Research Competition
Rangeet PanIowa State University, USA
02:10 - 03:00
Poster
ACM Student Research Competition
Tegan BrennanUniversity of California, Santa Barbara
02:10 - 03:00
Poster
ACM Student Research Competition
Xiyue ZhangPeking University