Thu 14 Nov 2019 12:10 - 12:20 at Cortez 2&3 - Deep Models Chair(s): Nazareno Aguirre
Deep neural network (DNN) has been widely applied to safety-critical scenarios such as autonomous vehicle, security surveillance, and cyber-physical control systems. Yet, the incorrect behaviors of DNNs can lead to severe accidents and tremendous losses due to hidden defects. In this paper, we present DeepHunter, a general-purpose fuzzing framework for detecting defects of DNNs. DeepHunter is inspired by traditional grey-box fuzzing and aims to increase the overall test coverage by applying adaptive heuristics according to runtime feedback. Specifically, DeepHunter provides a series of seed selection strategies, metamorphic mutation strategies, and testing criteria customized to DNN testing; all these components support multiple built-in configurations which are easy to extend. We evaluated DeepHunter on two popular datasets and the results demonstrate the effectiveness of DeepHunter in achieving coverage increase and detecting real defects. A video demonstration which showcases the main features of DeepHunter can be found at https://youtu.be/s5DfLErcgrc.
Tue 12 NovDisplayed time zone: Tijuana, Baja California change
10:00 - 10:40 | |||
10:00 40mDemonstration | Pangolin: An SFL-based Toolset for Feature Localization Demonstrations Bruno Miguel Sotto-Mayor de Castro Machado IST, University of Lisbon, Alexandre Perez Palo Alto Research Center, Rui Abreu Instituto Superior Técnico, U. Lisboa & INESC-ID | ||
10:00 40mDemonstration | A Quantitative Analysis Framework for Recurrent Neural Network Demonstrations Xiaoning Du Nanyang Technological University, Xiaofei Xie Nanyang Technological University, Yi Li Nanyang Technological University, Lei Ma Kyushu University, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University | ||
10:00 40mDemonstration | Ares: Inferring Error Specifications through Static Analysis Demonstrations Li Chi Tsinghua University, Zuxing Gu School of Software, Tsinghua University, Min Zhou Tsinghua University, Ming Gu Tsinghua University, Hongyu Zhang The University of Newcastle | ||
10:00 40mDemonstration | SiMPOSE - Configurable N-Way Program Merging Strategies for Superimposition-based Analysis of Variant-Rich Software Demonstrations Dennis Reuling Software Engineering Group, University of Siegen, Udo Kelter Software Engineering Group, University of Siegen, Sebastian Ruland TU Darmstadt, Real-time Systems Lab, Malte Lochau TU Darmstadt Pre-print Media Attached File Attached | ||
10:00 40mDemonstration | VeriAbs : Verification by Abstraction and Test Generation Demonstrations Mohammad Afzal Tata Cosultancy Services, A Asia Tata Cosultancy Services, Avriti Chauhan Tata Cosultancy Services, Bharti Chimdyalwar Tata Consultancy Services, Priyanka Darke Tata Consultancy Services, Advaita Datar Tata Consultancy Services Ltd, Shrawan Kumar Tata Cosultancy Services, R Venkatesh Tata Research Development and Design Centre | ||
10:00 40mDemonstration | DeepHunter: A Coverage-Guided Fuzzer for Deep Neural Networks Demonstrations Xiaofei Xie Nanyang Technological University, Hongxu Chen Nanyang Technological University, Yi Li Nanyang Technological University, Lei Ma Kyushu University, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University | ||
10:00 40mDemonstration | SPrinter: A Static Checker for Finding Smart Pointer Errors in C++ Programs Demonstrations Xutong Ma Institute of Software, Chinese Academy of Sciences, Jiwei Yan Institute of Software, Chinese Academy of Sciences, Yaqi Li Institute of Software, Chinese Academy of Sciences, Jun Yan Institute of Software, Chinese Academy of Sciences, Jian Zhang Institute of Software, Chinese Academy of Sciences | ||
10:00 40mDemonstration | LIRAT: Layout and Image Recognition Driving Automated Mobile Testing of Cross-Platform Demonstrations Shengcheng Yu Nanjing University, China, Chunrong Fang Nanjing University, Yang Feng University of California, Irvine, Wenyuan Zhao Nanjing University, Zhenyu Chen Nanjing University File Attached | ||
10:00 40mDemonstration | FogWorkflowSim: An Automated Simulation Toolkit for Workflow Performance Evaluation in Fog Computing Demonstrations Xiao Liu School of Information Technology, Deakin University, Lingmin Fan School of Computer Science and Technology, Anhui University, Jia Xu School of Computer Science and Technology, Anhui University, Xuejun Li School of Computer Science and Technology, Anhui University, Lina Gong School of Computer Science and Technology, Anhui University, John Grundy Monash University, Yun Yang Swinburne University of Technology | ||
10:00 40mDemonstration | SGUARD: A Feature-based Clustering Tool for Effective Spreadsheet Defect Detection Demonstrations Da Li State Key Lab. for Novel Software Tech. and Dept. of Comp. Sci. and Tech., Nanjing University, Nanjing, China, Huiyan Wang State Key Lab. for Novel Software Tech. and Dept. of Comp. Sci. and Tech., Nanjing University, Nanjing, China, Chang Xu Nanjing University, Ruiqing Zhang Search Tech. Center Asia, Microsoft, Suzhou, China, Shing-Chi Cheung Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Xiaoxing Ma State Key Lab. for Novel Software Tech. and Dept. of Comp. Sci. and Tech., Nanjing University | ||
10:00 40mDemonstration | FPChecker: Detecting Floating-Point Exceptions in GPU Applications Demonstrations Ignacio Laguna Lawrence Livermore National Laboratory | ||
10:00 40mDemonstration | PMExec: An Execution Engine of Partial UML-RT Models Demonstrations Mojtaba Bagherzadeh Queen's University, Karim Jahed Queen's University, Nafiseh Kahani Queen's University, Juergen Dingel Queen's University, Kingston, Ontario Pre-print |
Thu 14 NovDisplayed time zone: Tijuana, Baja California change
10:40 - 12:20 | Deep ModelsResearch Papers / Demonstrations at Cortez 2&3 Chair(s): Nazareno Aguirre Dept. of Computer Science FCEFQyN, University of Rio Cuarto | ||
10:40 20mTalk | Wuji: Automatic Online Combat Game Testing Using Evolutionary Deep Reinforcement LearningACM SIGSOFT Distinguished Paper Award Research Papers Yan Zheng Tianjin University, Xiaofei Xie Nanyang Technological University, Ting Su ETH Zurich, Lei Ma Kyushu University, Jianye Hao Tianjin University, Zhaopeng Meng Tianjin University, Yang Liu Nanyang Technological University, Singapore, Ruimin Shen Fuxi AI Lab in Netease, Yinfeng Chen Fuxi AI Lab in Netease, Changjie Fan Fuxi AI Lab in Netease Link to publication Pre-print | ||
11:00 20mTalk | A Study of Oracle Approximations in Testing Deep Learning Libraries Research Papers | ||
11:20 20mTalk | Property Inference for Deep Neural Networks Research Papers Divya Gopinath Carnegie Mellon University, Hayes Converse The University of Texas at Austin, Corina S. Pasareanu Carnegie Mellon University Silicon Valley, NASA Ames Research Center, Ankur Taly Google | ||
11:40 20mTalk | An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms Research Papers Qianyu Guo Tianjin University, Sen Chen Nanyang Technological University, Singapore, Xiaofei Xie Nanyang Technological University, Lei Ma Kyushu University, Qiang Hu Kyushu University, Japan, Hongtao Liu Tianjin University, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University, Xiaohong Li TianJin University Pre-print | ||
12:00 10mDemonstration | DeepMutation++: a Mutation Testing Framework for Deep Learning Systems Demonstrations Qiang Hu Kyushu University, Japan, Lei Ma Kyushu University, Xiaofei Xie Nanyang Technological University, Bing Yu Kyushu University, Japan, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University | ||
12:10 10mDemonstration | DeepHunter: A Coverage-Guided Fuzzer for Deep Neural Networks Demonstrations Xiaofei Xie Nanyang Technological University, Hongxu Chen Nanyang Technological University, Yi Li Nanyang Technological University, Lei Ma Kyushu University, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University |