Certified Defenses against Adversarial Examples

@article{Raghunathan2018CertifiedDA,
  title={Certified Defenses against Adversarial Examples},
  author={Aditi Raghunathan and Jacob Steinhardt and Percy Liang},
  journal={CoRR},
  year={2018},
  volume={abs/1801.09344}
}
While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and adversarial training have been proposed, but often followed by new, stronger attacks that defeat these defenses. Can we somehow end this arms race? In this work, we study this problem for neural networks with one hidden layer. We first propose a method based on a… CONTINUE READING
Highly Influential
This paper has highly influenced a number of papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 46 citations. REVIEW CITATIONS

Topics

Statistics

05020172018
Citations per Year

Citation Velocity: 34

Averaging 34 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.