Explaining and Harnessing Adversarial Examples

Explore this paper's citation graph

Summary

It is argued that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature, supported by new quantitative results while giving the first explanation of the most intriguing fact about them: their generalization across architectures and training sets.

Type
preprint
Published
2014-12-19
Cited by
23,012
References
19
Access
Open access

Keywords

Adversarial system, Overfitting, MNIST database, Computer science, Machine learning

References

Cited by

Related papers