Backdoor Watermarking Deep Learning Classification Models With Deep Fidelity. (arXiv:2208.00563v1 [cs.CR])

Backdoor Watermarking is a promising paradigm to protect the copyright of
deep neural network (DNN) models for classification tasks. In the existing
works on this subject, researchers have intensively focused on watermarking
robustness, while fidelity, which is concerned with the original functionality,
has received less attention. In this paper, we show that the existing shared
notion of the sole measurement of learning accuracy is insufficient to
characterize backdoor fidelity. Meanwhile, we show that the analogous concept
of embedding distortion in …

backdoor classification deep learning fidelity