The authors prove that filter frequency components at certain frequencies are nearly unchanged by gradient descent when the layer input is low-frequency, and use these components as a fine-tuning-robust watermark.
Certified neural network watermarks with randomized smoothing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards the Resistance of Neural Network Watermarking to Fine-tuning
The authors prove that filter frequency components at certain frequencies are nearly unchanged by gradient descent when the layer input is low-frequency, and use these components as a fine-tuning-robust watermark.