Training set cleansing of backdoor poisoning by self-supervised representation learning

no code implementations • 19 Oct 2022 • H. Wang, S. Karami, O. Dia, H. Ritter, E. Emamjomeh-Zadeh, J. Chen, Z. Xiang, D. J. Miller, G. Kesidis

Using a feature embedding found by self-supervised representation learning, a data cleansing method, which combines sample filtering and re-labeling, is developed.

Data Poisoning Image Classification +1