Blogs (1) >>
ASE 2019
Sun 10 - Fri 15 November 2019 San Diego, California, United States
Thu 14 Nov 2019 11:20 - 11:40 at Cortez 2&3 - Deep Models Chair(s): Nazareno Aguirre

We present techniques for automatically inferring formal properties of feed-forward neural networks. We observe that a significant part (if not all) of the logic of feed forward networks is captured in the activation status (on or off) of its neurons. We propose to extract patterns based on neuron decisions as preconditions that imply certain desirable output property e.g., the prediction being a certain class. Together, the inferred preconditions and the output property form a {\em contract} for the network. We present techniques to extract input properties} encoding convex predicates on the input space that imply given output properties and layer properties, representing network properties captured in the hidden layers that imply the desired output behavior. We apply our techniques on networks for the MNIST and ACASXU applications. Our experiments highlight the use of the inferred properties in a variety of tasks, such as explaining predictions, providing robustness guarantees, simplifying proofs, and network distillation.

Thu 14 Nov

Displayed 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
20m
Talk
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
20m
Talk
A Study of Oracle Approximations in Testing Deep Learning Libraries
Research Papers
Mahdi Nejadgholi Concordia University, Jinqiu Yang Concordia University, Montreal, Canada
11:20
20m
Talk
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
20m
Talk
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, Li Xiaohong TianJin University
Pre-print
12:00
10m
Demonstration
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
10m
Demonstration
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