Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias. (arXiv:2202.10582v1 [cs.CR])

Backdoor attack is a new AI security risk that has emerged in recent years.
Drawing on the previous research of adversarial attack, we argue that the
backdoor attack has the potential to tap into the model learning process and
improve model performance. Based on Clean Accuracy Drop (CAD) in backdoor
attack, we found that CAD came out of the effect of pseudo-deletion of data. We
provided a preliminary explanation of this phenomenon from the perspective of
model classification boundaries and …

application attack backdoor bias data