Corpus ID: 202572988

White-Box Adversarial Defense via Self-Supervised Data Estimation

@article{Lin2019WhiteBoxAD,
  title={White-Box Adversarial Defense via Self-Supervised Data Estimation},
  author={Zudi Lin and Hanspeter Pfister and Ziming Zhang},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.06271}
}
  • Zudi Lin, Hanspeter Pfister, Ziming Zhang
  • Published in ArXiv 2019
  • Mathematics, Computer Science
  • In this paper, we study the problem of how to defend classifiers against adversarial attacks that fool the classifiers using subtly modified input data. In contrast to previous works, here we focus on the white-box adversarial defense where the attackers are granted full access to not only the classifiers but also defenders to produce as strong attacks as possible. In such a context we propose viewing a defender as a functional, a higher-order function that takes functions as its argument to… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 37 REFERENCES

    Intriguing properties of neural networks

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    ImageNet: A large-scale hierarchical image database

    VIEW 16 EXCERPTS
    HIGHLY INFLUENTIAL

    On the momentum term in gradient descent learning algorithms

    • Ning Qian
    • Mathematics, Computer Science, Medicine
    • Neural Networks
    • 1999
    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Explaining and Harnessing Adversarial Examples

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Defense Against Universal Adversarial Perturbations

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Self-supervised Learning for Spinal MRIs

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL