Improving neural network verification through spurious region guided refinement

• Main Authors: YANG, Pengfei, LI, Renjue, LI, Jianlin, HUANG, Cheng Chao, WANG, Jingyi, SUN, Jun, XUE, Bai, ZHANG, Lijun
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: deep neural networks; spurious regions; DeepPoly; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/6057; https://ink.library.smu.edu.sg/context/sis_research/article/7060/viewcontent/Yang2021_Chapter_ImprovingNeuralNetworkVerifica.pdf
• Institution: Singapore Management University

We propose a spurious region guided refinement approach for robustness verification of deep neural networks. Our method starts with applying the DeepPoly abstract domain to analyze the network. If the robustness property cannot be verified, the result is inconclusive. Due to the over-approximation,...