Smoothed Inference for Adversarially-Trained Models

Explore this paper's citation graph

Summary

This work examines the application of randomized smoothing as a way to improve performance on unperturbed data as well as to increase robustness to adversarial attacks, and finds it lends itself well for trading-off between the model inference complexity and its performance.

Type
preprint
Published
2019-11-17
Cited by
2
References
57
Access
Open access

Keywords

Computer science, Smoothing, Adversarial system, Inference, Classifier (UML)

References

Cited by

Related papers