TY - GEN
T1 - A New Poisoning Attacks on Deep Neural Networks
AU - Li, Jung Shian
AU - Peng, Yen Chu
AU - Liu, I-Hsien
AU - Liu, Chuan Gang
N1 - Funding Information:
The authors gratefully acknowledge the support of the Ministry of Science and Technology of the Republic of China under Grant MOST 109-2221-E-041-001-, MOST 110-2218-E-006-013-MBK and MOST MOST 111-2218-E-006-010-MBK
Publisher Copyright:
© 2022 ACM.
PY - 2022/5/15
Y1 - 2022/5/15
N2 - In healthcare field, many machine learning schemes have been applied in analyzing image content dataset. Among them, deep neural networks (DNNs), also known as deep learning, catches much attention. However, if deep neural networks are compromised by the attacker, medical diagnosis may be wrong, which leads to vital result. Recently, we find a new poisoning attack on DNNs may possibly happens due to poisoning dataset. This new poisoning attack, Category Diverse attack, has better ability to paralyze DNNs. Our performance experiments show our Category diverse attack actually leads to large accuracy drop of DNNs. We hope this discovery can help the information experts can improve the medical dataset quality in the future.
AB - In healthcare field, many machine learning schemes have been applied in analyzing image content dataset. Among them, deep neural networks (DNNs), also known as deep learning, catches much attention. However, if deep neural networks are compromised by the attacker, medical diagnosis may be wrong, which leads to vital result. Recently, we find a new poisoning attack on DNNs may possibly happens due to poisoning dataset. This new poisoning attack, Category Diverse attack, has better ability to paralyze DNNs. Our performance experiments show our Category diverse attack actually leads to large accuracy drop of DNNs. We hope this discovery can help the information experts can improve the medical dataset quality in the future.
UR - http://www.scopus.com/inward/record.url?scp=85136938900&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136938900&partnerID=8YFLogxK
U2 - 10.1145/3545729.3545736
DO - 10.1145/3545729.3545736
M3 - Conference contribution
AN - SCOPUS:85136938900
T3 - ACM International Conference Proceeding Series
SP - 24
EP - 27
BT - ICMHI 2022 - 2022 6th International Conference on Medical and Health Informatics
PB - Association for Computing Machinery
T2 - 6th International Conference on Medical and Health Informatics, ICMHI 2022
Y2 - 12 May 2022 through 15 May 2022
ER -