RNNRepair: Automatic RNN Repair via model-based analysis

• Main Authors: XIE, Xiaofei, GUO, Wenbo, MA, Lei, LE, Wei, WANG, Jian, ZHOU, Lingjun, LIU, Yang, XING, Xinyu
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Information Security; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/6938; https://ink.library.smu.edu.sg/context/sis_research/article/7941/viewcontent/xie21b_pvoa.pdf
• Institution: Singapore Management University

Deep neural networks are vulnerable to adversarial attacks. Due to their black-box nature, it is rather challenging to interpret and properly repair these incorrect behaviors. This paper focuses on interpreting and repairing the incorrect behaviors of Recurrent Neural Networks (RNNs). We propose a l...