Corpus ID: 218763634

Revisiting Role of Autoencoders in Adversarial Settings

@article{Kim2020RevisitingRO,
  title={Revisiting Role of Autoencoders in Adversarial Settings},
  author={Byeong Cheon Kim and Jung Uk Kim and Hakmin Lee and Yong Man Ro},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10750}
}
  • Byeong Cheon Kim, Jung Uk Kim, +1 author Yong Man Ro
  • Published 2020
  • Computer Science
  • ArXiv
  • To combat against adversarial attacks, autoencoder structure is widely used to perform denoising which is regarded as gradient masking. In this paper, we revisit the role of autoencoders in adversarial settings. Through the comprehensive experimental results and analysis, this paper presents the inherent property of adversarial robustness in the autoencoders. We also found that autoencoders may use robust features that cause inherent adversarial robustness. We believe that our discovery of the… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES

    Combatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approach

    VIEW 2 EXCERPTS

    Improving Adversarial Robustness via Guided Complement Entropy

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser

    VIEW 2 EXCERPTS

    Adversarial Examples Are Not Bugs, They Are Features

    VIEW 1 EXCERPT