Multiple Classifier Systems under Attack

By Battista Biggio, Giorgio Fumera, Fabio Roli. 2010

56 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Signal Processing

How researchers see this paper

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

In Computer Networks and Communications

In Information Systems

In Signal Processing

Citations in the corpus

Adversarial Feature Selection Against Evasion Attacks (2016, background): “Multiple classifier systems, which have been originally proposed to improve classification accuracy through the combination of weaker classifiers, have also been exploited to the same end [15], [16], [31].”
Support vector machines under adversarial label contamination (2015, background): “Keywords: Support Vector Machines, Adversarial Learning, Label Noise, Label Flip Attacks”
Pattern Recognition Systems under Attack: Design Issues and Research Challenges (2014, background): “Multiple Classifier Systems (MCSs) have been exploited for different purposes in adversarial settings, in particular, to improve security against evasion attempts [47, 17, 15, 16, 18] and against poisoning of the training data [9].”
Adversarial machine learning (2019, background): “promote randomized classifiers as a defense against exploratory evasion [4].”
Optimization Models for Machine Learning: A Survey (2019, background): “A large number of contributions in the literature pointed out the dangers caused by perturbed examples, also called adversarial examples, causing classification errors [34, 195].”
Cracking Classifiers for Evasion: A Case Study on the Google's Phishing Pages Filter (2016, background): “MCSs [13][14][15], as the name suggests, uses multiple classifiers rather than only one to improve classifier’s robustness.”
Classifier Evasion: Models and Open Problems (2010, methodology): “Biggio et al. [3] extend this game-theoretic approach and propose hiding information or randomization as additional defense mechanisms for this setting.”
Multiple classifier systems for robust classifier design in adversarial environments (2010, methodology): “[6,7] with a more thorough discussion on bagging and the RSM, and a more extensive experimental investigation.”
Behavior of Machine Learning Algorithms in Adversarial Environments (2010, methodology): “Based on this argument, Biggio et al. [2010] promote randomized classifiers as a defense against evasion.”
One-and-a-Half-Class Multiple Classifier Systems for Secure Learning Against Evasion Attacks at Test Time (2015, methodology): “Linear classifiers exhibiting the aforementioned behavior have been implemented efficiently using MCSs, by averaging an ensemble of linear classifiers [23,26,27,18].”