Multiple classifier systems for robust classifier design in adversarial environments

@article{Biggio2010MultipleCS,
  title={Multiple classifier systems for robust classifier design in adversarial environments},
  author={B. Biggio and G. Fumera and F. Roli},
  journal={International Journal of Machine Learning and Cybernetics},
  year={2010},
  volume={1},
  pages={27-41}
}
Pattern recognition systems are increasingly being used in adversarial environments like network intrusion detection, spam filtering and biometric authentication and verification systems, in which an adversary may adaptively manipulate data to make a classifier ineffective. Current theory and design methods of pattern recognition systems do not take into account the adversarial nature of such kind of applications. Their extension to adversarial settings is thus mandatory, to safeguard the… Expand
166 Citations
Design of robust classifiers for adversarial environments
  • 37
  • PDF
Security Evaluation of Pattern Classifiers under Attack
  • 315
  • PDF
Support vector machines under adversarial label contamination
  • 127
  • PDF
On Security and Sparsity of Linear Classifiers for Adversarial Settings
  • 22
  • PDF
One-and-a-Half-Class Multiple Classifier Systems for Secure Learning Against Evasion Attacks at Test Time
  • 37
  • PDF
A System-Driven Taxonomy of Attacks and Defenses in Adversarial Machine Learning
  • 1
A Comprehensive Survey on Pattern Classifier's Security Evaluation under Attack
On learning and recognition of secure patterns
  • PDF
Adversarial Feature Selection Against Evasion Attacks
  • 159
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 59 REFERENCES
Multiple Classifier Systems under Attack
  • 39
  • PDF
Adversarial Pattern Classification Using Multiple Classifiers and Randomisation
  • 60
  • PDF
Evade Hard Multiple Classifier Systems
  • 21
  • PDF
Evaluation of classifiers: Practical considerations for security applications
  • 35
  • PDF
Adversarial learning
  • 584
  • PDF
Adversarial classification
  • 720
  • PDF
Feature Weighting for Improved Classifier Robustness
  • 130
  • Highly Influential
  • PDF
Can machine learning be secure?
  • 636
  • PDF
Using an Ensemble of One-Class SVM Classifiers to Harden Payload-based Anomaly Detection Systems
  • 214
  • PDF
...
1
2
3
4
5
...