WPDA: Frequency-based Backdoor Attack with Wavelet Packet Decomposition. (arXiv:2401.13578v1 [cs.CR])

This work explores an emerging security threat against deep neural networks
(DNNs) based image classification, i.e., backdoor attack. In this scenario, the
attacker aims to inject a backdoor into the model by manipulating training
data, such that the backdoor could be activated by a particular trigger and
bootstraps the model to make a target prediction at inference. Currently, most
existing data poisoning-based attacks struggle to achieve success at low
poisoning ratios, increasing the risk of being defended by defense methods. …

arxiv attack attacker backdoor classification data emerging image inject networks neural networks packet scenario security security threat threat training training data trigger work