Stealing Machine Learning Models via Prediction APIs

A theory of the learnable

1984

Earlier work this paper cites.

Queries and concept learning

1988

Earlier work this paper cites.

Approximation by superpositions of a sigmoidal function

1989

Earlier work this paper cites.

Multilayer feedforward networks are universal approximators

1989

Earlier work this paper cites.

Occam’s razor

1990

Earlier work this paper cites.

Learnability with respect to fixed distributions

1991

Earlier work this paper cites.

A technique for upper bounding the spectral norm with applications to learning

1992

Earlier work this paper cites.

A training algorithm for optimal margin classifiers

1992

Earlier work this paper cites.

Learning decision trees using the Fourier spectrum

1993

Earlier work this paper cites.

Extracting refined rules from knowledge-based neural networks

1993

Earlier work this paper cites.

Improving generalization with active learning

1994

Earlier work this paper cites.

An efficient membership-query algorithm for learning DNF with respect to the uniform distribution

1994

Earlier work this paper cites.

Survey and critique of techniques for extracting rules from trained artificial neural networks

1995

Earlier work this paper cites.

Exact learning boolean functions via the monotone theory

1995

Earlier work this paper cites.

Active learning literature survey

1995

Earlier work this paper cites.

Extracting tree-structured representations of trained networks

1996

Earlier work this paper cites.

Selection of relevant features and examples in machine learning

1997

Earlier work this paper cites.

Kernel logistic regression and the import vector machine

Original

2001

Earlier work this paper cites.

Adversarial classification

2004

Earlier work this paper cites.

Adversarial learning

2005

Cited alongside, same era.

Good word attacks on statistical spam filters

2005

Cited alongside, same era.

Can machine learning be secure?

2006

Cited alongside, same era.

Model compression

2006

Cited alongside, same era.

Differential privacy

2006

Cited alongside, same era.

Paragraph: Thwarting signature learning by training maliciously

2006

Cited alongside, same era.

Numerical optimization

2006

Cited alongside, same era.

Evasion attacks against machine learning at test time

2013

Later among the works it cites.

Membership privacy: A unifying framework for privacy definitions

2013

Later among the works it cites.

UCI machine learning repository, 2013

2013

Later among the works it cites.

General social surveys, 1972-2012, 2013

2013

Later among the works it cites.

On the hardness of evading combinations of linear classifiers

2013

Later among the works it cites.

Privacy in pharmacogenetics: An end-to-end case study of personalized Warfarin dosing

2014

Later among the works it cites.

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