Attention Distraction: Watermark Removal Through Continual Learning with Selective Forgetting. (arXiv:2204.01934v1 [cs.CV])

Fine-tuning attacks are effective in removing the embedded watermarks in deep
learning models. However, when the source data is unavailable, it is
challenging to just erase the watermark without jeopardizing the model
performance. In this context, we introduce Attention Distraction (AD), a novel
source data-free watermark removal attack, to make the model selectively forget
the embedded watermarks by customizing continual learning. In particular, AD
first anchors the model's attention on the main task using some unlabeled data.
Then, through continual …

attention