Searched for: +
(1 - 2 of 2)
document
Zhao, Zhendong (author), Chen, Xiaojun (author), Xuan, Yuexin (author), Dong, Ye (author), Wang, Dakui (author), Liang, K. (author)
Backdoor attack is a type of serious security threat to deep learning models. An adversary can provide users with a model trained on poisoned data to manipulate prediction behavior in test stage using a backdoor. The backdoored models behave normally on clean images, yet can be activated and output incorrect prediction if the input is stamped...
conference paper 2022
document
Liang, Jianwen (author), van der Maas, E.L. (author), Luo, Jing (author), Li, Xiaona (author), Chen, Ning (author), Adair, Keegan R. (author), Li, Weihan (author), Li, Junjie (author), Hu, Yongfeng (author), Liu, Jue (author), Zhang, Li (author), Zhao, W. (author), Parnell, S.R. (author), Ganapathy, S. (author), Wagemaker, M. (author)
Understanding the relationship between structure, ionic conductivity, and synthesis is the key to the development of superionic conductors. Here, a series of Li<sub>3-3</sub><sub>x</sub>M<sub>1+</sub><sub>x</sub>Cl<sub>6</sub> (−0.14 &lt; x ≤ 0.5, M = Tb, Dy, Ho, Y, Er, Tm) solid electrolytes with orthorhombic and trigonal structures are...
journal article 2022