Fetching the paper…
Reading the bibliography…
This manuscript presents some new impossibility results on adversarial robustness in machine learning, a very important yet largely open problem.
Diffusions hypercontractives
Bakry, D. and Émery, M · 1985
Earlier work this paper cites.
Exponential integrability and transportation cost related to logarithmic sobolev inequalities
Bobkov, S. and Goetze, F · 1999
Earlier work this paper cites.
Generalization of an inequality by talagrand and links with the logarithmic sobolev inequality
Otto, F. and Villani, C · 2000
Earlier work this paper cites.
Transportation cost-information inequalities and applications to random dynamical systems and diffusions
Djellout, H., Guillin, A., and Wu, L · 2004
Earlier work this paper cites.
Calculation of differential entropy for a mixed gaussian distribution
Michalowicz, J. V., Nichols, J. M., and Bucholtz, F · 2008
Earlier work this paper cites.
Optimal Transport: Old and New
Villani, C · 2008
Earlier work this paper cites.
MNIST handwritten digit database
LeCun, Y. and Cortes, C · 2010
Cited alongside, same era.
Concentration Inequalities: A Nonasymptotic Theory of Independence
Boucheron, S., Lugosi, G., and Massart, P · 2013
Cited alongside, same era.
Quantifying distributional model risk via optimal transport, 2016
Blanchet, J. and Murthy, K. R. A · 2016
Cited alongside, same era.
Data-driven distributionally robust optimization using the wasserstein metric: performance guarantees and tractable reformulations
Mohajerin Esfahani, P. and Kuhn, D · 2017
Cited alongside, same era.
Certifiable distributional robustness with principled adversarial training
Sinha, A., Namkoong, H., and Duchi, J. C · 2017
Cited alongside, same era.
Adversarial examples from computational constraints
Bubeck, S., Price, E., and Razenshteyn, I. P · 2018
Closest in time.
Mahloujifar, S., Diochnos, D. I., and Mahmoody, M · 2018
Closest in time.
Adversarially robust generalization requires more data
Schmidt, L., Santurkar, S., Tsipras, D., Talwar, K., and Madry, A · 2018
Closest in time.
Are adversarial examples inevitable?
Shafahi, A., Huang, W. R., Studer, C., Feizi, S., and Goldstein, T · 2018
Closest in time.
There is no free lunch in adversarial robustness (but there are unexpected benefits)
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Su, J., Vargas, D. V., and Sakurai, K · 2017
Cited alongside, same era.
Adversarial vulnerability for any classifier
Fawzi, A., Fawzi, H., and Fawzi, O
Cited in the paper.
Empirical study of the topology and geometry of deep networks
Fawzi, A., Moosavi-Dezfooli, S.-M., Frossard, P., and Soatto, S
Cited in the paper.
Motivating the rules of the game for adversarial example research
Gilmer, J., Adams, R. P., Goodfellow, I. J., Andersen, D., and Dahl, G. E
Cited in the paper.
Gilmer, J., Metz, L., Faghri, F., Schoenholz, S. S., Raghu, M., Wattenberg, M., and Goodfellow, I. J
Cited in the paper.
Tsipras, D., Santurkar, S., Engstrom, L., Turner, A., and Madry, A · 2018
Closest in time.