Adversarial Robustness Curves

@inproceedings{Gopfert2019AdversarialRC,
  title={Adversarial Robustness Curves},
  author={Christina Gopfert and Jan Philip G{\"o}pfert and B. Hammer},
  booktitle={PKDD/ECML Workshops},
  year={2019}
}
  • Christina Gopfert, Jan Philip Göpfert, B. Hammer
  • Published in PKDD/ECML Workshops 2019
  • Computer Science, Mathematics
  • The existence of adversarial examples has led to considerable uncertainty regarding the trust one can justifiably put in predictions produced by automated systems. This uncertainty has, in turn, lead to considerable research effort in understanding adversarial robustness. In this work, we take first steps towards separating robustness analysis from the choice of robustness threshold and norm. We propose robustness curves as a more general view of the robustness behavior of a model and… CONTINUE READING
    3 Citations

    Figures and Topics from this paper

    Explore Further: Topics Discussed in This Paper

    Adversarial examples and where to find them
    How to compare adversarial robustness of classifiers from a global perspective
    • PDF
    A general framework for defining and optimizing robustness
    • PDF

    References

    SHOWING 1-10 OF 20 REFERENCES
    Learning with a Strong Adversary
    • 210
    • PDF
    Robustness May Be at Odds with Accuracy
    • 546
    • Highly Influential
    • PDF
    Adversarial Robustness May Be at Odds With Simplicity
    • 49
    • PDF
    Measuring Neural Net Robustness with Constraints
    • 227
    • PDF
    Adversarial attacks hidden in plain sight
    • 5
    • PDF
    Towards Evaluating the Robustness of Neural Networks
    • 2,943
    • PDF
    Explaining and Harnessing Adversarial Examples
    • 6,261
    • PDF
    Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks
    • 1,516
    • PDF
    Towards Deep Neural Network Architectures Robust to Adversarial Examples
    • 486
    • PDF
    Adversarial Machine Learning at Scale
    • 1,225
    • PDF