Stealing deep reinforcement learning models for fun and profit

• Main Authors: CHEN, Kangjie, GUO, Shangwei, ZHANG, Tianwei, XIE, Xiaofei, LIU, Yang
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2021
• 主題: Model extraction; Deep reinforcement learning; Imitation learning; Software Engineering
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/7110; https://ink.library.smu.edu.sg/context/sis_research/article/8113/viewcontent/3433210.3453090.pdf
• 機構: Singapore Management University

This paper presents the first model extraction attack against Deep Reinforcement Learning (DRL), which enables an external adversary to precisely recover a black-box DRL model only from its interaction with the environment. Model extraction attacks against supervised Deep Learning models have been w...