Corpus ID: 208139043

REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data

@article{Chen2019REFITAU,
  title={REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data},
  author={Xinyun Chen and Wenxiao Wang and Christopher Bender and Yiming Ding and Ruoxi Jia and Bo Li and Dawn Xiaodong Song},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.07205}
}
  • Xinyun Chen, Wenxiao Wang, +4 authors Dawn Xiaodong Song
  • Published 2019
  • Computer Science
  • ArXiv
  • Deep neural networks (DNNs) have achieved tremendous success in various fields; however, training these models from scratch could be computationally expensive and requires a lot of training data. Recent work has explored different watermarking techniques to protect the pre-trained deep neural networks from potential copyright infringements; however, they could be vulnerable to adversaries who aim at removing the watermarks. In this work, we propose REFIT, a unified watermark removal framework… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 56 REFERENCES

    Robust Watermarking of Neural Network with Exponential Weighting

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Adversarial frontier stitching for remote neural network watermarking

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Protecting Intellectual Property of Deep Neural Networks with Watermarking

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks

    VIEW 1 EXCERPT