Corpus ID: 218763633

Model-Based Robust Deep Learning

@article{Robey2020ModelBasedRD,
  title={Model-Based Robust Deep Learning},
  author={Alexander Robey and Hamed Hassani and George J. Pappas},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10247}
}
  • Alexander Robey, Hamed Hassani, George J. Pappas
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • While deep learning has resulted in major breakthroughs in many application domains, the frameworks commonly used in deep learning remain fragile to artificially-crafted and imperceptible changes in the data. In response to this fragility, adversarial training has emerged as a principled approach for enhancing the robustness of deep learning with respect to norm-bounded perturbations. However, there are other sources of fragility for deep learning that are arguably more common and less… CONTINUE READING

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 111 REFERENCES

    Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid

    VIEW 1 EXCERPT

    Robust Physical-World Attacks on Deep Learning Visual Classification

    VIEW 2 EXCERPTS

    One Pixel Attack for Fooling Deep Neural Networks

    VIEW 1 EXCERPT

    Boosting Adversarial Attacks with Momentum

    VIEW 1 EXCERPT