Practical Black-Box Attacks against Machine Learning

Random sampling with a reservoir

Jeffrey S Vitter · 1985

Earlier work this paper cites.

The mnist database of handwritten digits, 1998

Yann LeCun et al · 1998

Earlier work this paper cites.

Can machine learning be secure?

Marco Barreno, et al · 2006

Earlier work this paper cites.

Testing Statistical Hypotheses

Erich L. Lehmann, et al · 2008

Earlier work this paper cites.

Adversarial machine learning

Ling Huang, et al · 2011

Earlier work this paper cites.

Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition

Johannes Stallkamp, et al · 2012

Earlier work this paper cites.

Evasion attacks against machine learning at test time

Battista Biggio, et al · 2013

Cited alongside, same era.

Intriguing properties of neural networks

Christian Szegedy, et al · 2014

Cited alongside, same era.

Explaining and harnessing adversarial examples

Ian J Goodfellow, et al · 2015

Cited alongside, same era.

Deep learning

Ian Goodfellow, et al · 2016

Cited alongside, same era.

Adversarial examples in the physical world

Original

Alexey Kurakin, et al · 2016

Cited alongside, same era.

Distillation as a defense to adversarial perturbations against deep neural networks

Nicolas Papernot, et al

Cited in the paper.

Practical evasion of a learning-based classifier: A case study

Nedim Srndic, et al

Cited in the paper.

The limitations of deep learning in adversarial settings

Nicolas Papernot, et al · 2016

Closest in time.

Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition

Mahmood Sharif, et al · 2016

Closest in time.

Stealing machine learning models via prediction apis

Florian Tramèr, et al · 2016

Closest in time.

Adversarial perturbations of deep neural networks

D Warde-Farley, et al · 2016

Closest in time.

Automatically evading classifiers

Weilin Xu, et al · 2016

Closest in time.