Corpus ID: 8839470

Building Better Detection with Privileged Information

@article{Celik2016BuildingBD,
  title={Building Better Detection with Privileged Information},
  author={Z. Y. Celik and P. McDaniel and R. Izmailov and Nicolas Papernot and A. Swami},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.09638}
}
  • Z. Y. Celik, P. McDaniel, +2 authors A. Swami
  • Published 2016
  • Computer Science, Mathematics
  • ArXiv
  • Modern detection systems use sensor outputs available in the deployment environment to probabilistically identify attacks. These systems are trained on past or synthetic feature vectors to create a model of anomalous or normal behavior. Thereafter, run-time collected sensor outputs are compared to the model to identify attacks (or the lack of attack). While this approach to detection has been proven to be effective in many environments, it is limited to training on only features that can be… CONTINUE READING
    1 Citations
    Microsoft Malware Classification Challenge
    • 117
    • PDF

    References

    SHOWING 1-10 OF 52 REFERENCES
    Sequential anomaly detection in a batch with growing number of tests: Application to network intrusion detection
    • 11
    A Flow Classifier with Tamper-Resistant Features and an Evaluation of Its Portability to New Domains
    • 14
    Intrusion detection and Big Heterogeneous Data: a Survey
    • 194
    Detection of Fast-Flux Networks using various DNS feature sets
    • Z. Y. Celik, S. Oktug
    • Computer Science
    • 2013 IEEE Symposium on Computers and Communications (ISCC)
    • 2013
    • 25
    • PDF
    Classifier learning with hidden information
    • Ziheng Wang, Q. Ji
    • Computer Science
    • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2015
    • 49
    • PDF