Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution

Dimitrios Diochnos; Saeed Mahloujifar; Mohammad Mahmoody

NeurIPS 2018poster95 citations

Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution

Dimitrios Diochnos, Saeed Mahloujifar, Mohammad Mahmoody

Abstract

We study adversarial perturbations when the instances are uniformly distributed over {0,1}^n. We study both "inherent" bounds that apply to any problem and any classifier for such a problem as well as bounds that apply to specific problems and specific hypothesis classes.

BibTeX

@inproceedings{NEURIPS2018_3483e5ec,
 author = {Diochnos, Dimitrios and Mahloujifar, Saeed and Mahmoody, Mohammad},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/3483e5ec0489e5c394b028ec4e81f3e1-Paper.pdf},
 volume = {31},
 year = {2018}
}