TY - JOUR
T1 - 机器学习模型安全与隐私研究综述
AU - Ji, Shou Ling
AU - Du, Tian Yu
AU - Li, Jin Feng
AU - Shen, Chao
AU - Li, Bo
N1 - Funding Information:
基金项目: 国家重点研发计划(2018YFB0804102); 浙江省自然科学基金(LR19F020003); 浙江省科技计划(2019C01055); 国家 自然科学基金(61772466, U1936215, U1836202, 61822309, 61773310, U1736205) Foundation item: National Key Researchand Development Program of China (2018YFB0804102); Zhejiang Provincial Natural Science Foundation of China (LR19F020003); Provincial Key Research and Development Program of Zhejiang, China (2019C01055); National Natural Science Foundation of China (61772466, U1936215, U1836202, 61822309, 61773310, U1736205) 收稿时间: 2019-06-10; 修改时间: 2019-10-01; 采用时间: 2020-08-17; jos 在线出版时间: 2020-09-10
Publisher Copyright:
© Copyright 2021, Institute of Software, the Chinese Academy of Sciences. All rights reserved.
PY - 2021/1
Y1 - 2021/1
N2 - In the era of big data, breakthroughs in theories and technologies of deep learning, reinforcement learning, and distributed learning have provided strong support for machine learning at the data and the algorithm level, as well as have promoted the development of scale and industrialization of machine learning. However, though machine learning models have excellent performance in many real-world applications, they still suffer many security and privacy threats at the data, model, and application levels, which could be characterized by diversity, concealment, and dynamic evolution. The security and privacy issues of machine learning have attracted extensive attention from academia and industry. A large number of researchers have conducted in-depth research on the security and privacy issues of models from the perspective of attack and defense, and proposed a series of attack and defense methods. In this survey, the security and privacy issues of machine learning are reviewed, existing research work is systematically and scientifically summarized, and the advantages and disadvantages of current research are clarified. Finally, the current challenges and future research directions of machine learning model security and privacy research are explored, aiming to provide guidance for follow-up researchers to further promote the development and application of machine learning model security and privacy research.
AB - In the era of big data, breakthroughs in theories and technologies of deep learning, reinforcement learning, and distributed learning have provided strong support for machine learning at the data and the algorithm level, as well as have promoted the development of scale and industrialization of machine learning. However, though machine learning models have excellent performance in many real-world applications, they still suffer many security and privacy threats at the data, model, and application levels, which could be characterized by diversity, concealment, and dynamic evolution. The security and privacy issues of machine learning have attracted extensive attention from academia and industry. A large number of researchers have conducted in-depth research on the security and privacy issues of models from the perspective of attack and defense, and proposed a series of attack and defense methods. In this survey, the security and privacy issues of machine learning are reviewed, existing research work is systematically and scientifically summarized, and the advantages and disadvantages of current research are clarified. Finally, the current challenges and future research directions of machine learning model security and privacy research are explored, aiming to provide guidance for follow-up researchers to further promote the development and application of machine learning model security and privacy research.
KW - Adversarial example
KW - Artificial intelligence security
KW - Machine learning
KW - Model privacy
KW - Poisoning attack
UR - http://www.scopus.com/inward/record.url?scp=85099098175&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099098175&partnerID=8YFLogxK
U2 - 10.13328/j.cnki.jos.006131
DO - 10.13328/j.cnki.jos.006131
M3 - Review article
AN - SCOPUS:85099098175
VL - 32
SP - 41
EP - 67
JO - Ruan Jian Xue Bao/Journal of Software
JF - Ruan Jian Xue Bao/Journal of Software
SN - 1000-9825
IS - 1
ER -