Discriminative Direction for Kernel Classifiers

By Polina Golland. 2001

34 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Artificial Intelligence, Geometry and Topology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

1. Battista Biggio
2. Fabio Roli
3. Giorgio Fumera
4. Pavel Laskov
5. Giorgio Giacinto
6. Benjamin I. P. Rubinstein
7. Nedim Srndic
8. Igino Corona

In Artificial Intelligence

1. Battista Biggio
2. Fabio Roli
3. Giorgio Giacinto
4. Davide Maiorca
5. Giorgio Fumera
6. Nicolas Papernot
7. Nicholas Carlini
8. Igino Corona

In Geometry and Topology

1. Battista Biggio
2. Fabio Roli
3. Giorgio Fumera
4. Pavel Laskov
5. Giorgio Giacinto
6. Benjamin I. P. Rubinstein
7. Nedim Srndic
8. Igino Corona

Citations in the corpus

• Evasion Attacks against Machine Learning at Test Time (2013, methodology): “In contrast, the methods presented in Sections 2 and 3 can generally evade linear or non-linear classifiers using a gradient-descent approach inspired by Golland’s discriminative directions technique [13].”
• Security Evaluation of Support Vector Machines in Adversarial Environments (2014, positive): “In contrast to this prior work, the methods presented in our recent work [8] and in this section demonstrate that evasion of kernel-based classifiers at test time can be realized with a straightforward gradient-descent-based approach derived from Golland’s technique of discriminative directions [33]”
• BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm (2004, background): “This can be done by analyzing the so-called discriminative directions from the Support Vectors of a trained SVM [10].”