TY - GEN
T1 - Reluplex made more practical
T2 - 2020 IEEE Symposium on Computers and Communications, ISCC 2020
AU - Xu, Jin
AU - Li, Zishan
AU - Du, Bowen
AU - Zhang, Miaomiao
AU - Liu, Jing
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/7
Y1 - 2020/7
N2 - In recent years, Deep Neural Networks (DNNs) have been experiencing rapid development and have been widely used in various fields. However, while DNNs have shown strong capabilities, their security problems have gradually been exposed. Therefore, the formal guarantee of neural network output is needed. Prior to the appearance of the Reluplex algorithm, the verification of DNNs was always a difficult problem. Reluplex algorithm is specially used to verify DNNs with ReLU activation function. This is an excellent and effective algorithm, but it cannot verify more activation functions. ReLU activation function will bring about "Dead Neuron"problem, and Leaky ReLU activation function can solve this problem, so it is necessary to verify DNNs based on Leaky ReLU activation function. Therefore, we propose the Leaky-Reluplex algorithm, which is based on the Reluplex algorithm. Leaky-Reluplex algorithm can verify DNNs based on Leaky ReLU activation function.
AB - In recent years, Deep Neural Networks (DNNs) have been experiencing rapid development and have been widely used in various fields. However, while DNNs have shown strong capabilities, their security problems have gradually been exposed. Therefore, the formal guarantee of neural network output is needed. Prior to the appearance of the Reluplex algorithm, the verification of DNNs was always a difficult problem. Reluplex algorithm is specially used to verify DNNs with ReLU activation function. This is an excellent and effective algorithm, but it cannot verify more activation functions. ReLU activation function will bring about "Dead Neuron"problem, and Leaky ReLU activation function can solve this problem, so it is necessary to verify DNNs based on Leaky ReLU activation function. Therefore, we propose the Leaky-Reluplex algorithm, which is based on the Reluplex algorithm. Leaky-Reluplex algorithm can verify DNNs based on Leaky ReLU activation function.
KW - Deep Neural Networks
KW - Leaky ReLU
KW - Reluplex Algorithm
UR - https://www.scopus.com/pages/publications/85094170162
U2 - 10.1109/ISCC50000.2020.9219587
DO - 10.1109/ISCC50000.2020.9219587
M3 - 会议稿件
AN - SCOPUS:85094170162
T3 - Proceedings - IEEE Symposium on Computers and Communications
BT - 2020 IEEE Symposium on Computers and Communications, ISCC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 7 July 2020 through 10 July 2020
ER -