Automatically Evading Classifiers: A Case Study on PDF Malware Classifiers

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  author =       "Weilin Xu and Yanjun Qi and David Evans",
  title =        "Automatically Evading Classifiers: A Case Study on PDF
                 Malware Classifiers",
  booktitle =    "The Network and Distributed System Security Symposium
  year =         "2016",
  editor =       "Lujo Bauer and Karen O'Donoghue",
  address =      "San Diego, USA",
  month =        "21-24 " # feb,
  keywords =     "genetic algorithms, genetic programming, genetic
  URL =          "",
  URL =          "",
  URL =          "",
  size =         "15 pages",
  abstract =     "Machine learning is widely used to develop classifiers
                 for security tasks. However, the robustness of these
                 methods against motivated adversaries is uncertain. In
                 this work, we propose a generic method to evaluate the
                 robustness of classifiers under attack. The key idea is
                 to stochastically manipulate a malicious sample to find
                 a variant that preserves the malicious behaviour but is
                 classified as benign by the classifier. We present a
                 general approach to search for evasive variants and
                 report on results from experiments using our techniques
                 against two PDF malware classifiers, PDFrate and
                 Hidost. Our method is able automatically find evasive
                 variants for all of the 500 malicious seeds in our
                 study. Our results suggest a general method for
                 evaluating classifiers used in security applications,
                 and raise serious doubts about the effectiveness of
                 classifiers based on superficial features in the
                 presence of adversaries.",
  notes =        "",

Genetic Programming entries for Weilin Xu Yanjun Qi David Evans