Evade Hard Multiple Classifier Systems
By Battista Biggio, Giorgio Fumera, Fabio Roli. 2009
25 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
- Battista Biggio
- Fabio Roli
- Giorgio Fumera
- Daniel S. Yeung
- Patrick P. K. Chan
- Fei Zhang
- Giorgio Giacinto
- Davide Maiorca
In Information Systems
- Fabio Roli
- Battista Biggio
- Giorgio Fumera
- Daniel S. Yeung
- Patrick P. K. Chan
- Fei Zhang
- Blaine Nelson
- Giorgio Giacinto
In Signal Processing
- Battista Biggio
- Fabio Roli
- Giorgio Fumera
- Daniel S. Yeung
- Patrick P. K. Chan
- Fei Zhang
- Giorgio Giacinto
- Davide Maiorca
Citations in the corpus
- Adversarial Feature Selection Against Evasion Attacks (2016, background): “in [34] and [43] the authors have proposed a measure of classifier security against evasion attacks, called hardness of”
- Multiple Classifier Systems under Attack (2010, background): “Since adding new detection rules to a system in response to new attacks is a common practice in spam filtering and in intrusion detection in computer systems, in [14] we investigated whether adding classifiers to a given ensemble can improve its robustness.”
- Multiple Classifier Systems for Adversarial Classification Tasks (2009, background): “However, with the only exception of a previous work by the authors [11], the use of MCSs for improving the hardness of evasion is supported only by intuitive and qualitative motivations, besides experimental evidences, and lack of a clear and sound theoretical support.”
- 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].”
- Multiple classifier systems for robust classifier design in adversarial environments (2010, background): “Since adding new detection rules to a system in response to new attacks is a common practice in spam filtering and in network intrusion detection, in [5] we investigated whether adding classifiers to a given ensemble improves its robustness.”