Paragraph: Thwarting Signature Learning by Training Maliciously

  • James Newsome
  • Brad Karp
  • Dawn Song
Conference paper

DOI: 10.1007/11856214_5

Volume 4219 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Newsome J., Karp B., Song D. (2006) Paragraph: Thwarting Signature Learning by Training Maliciously. In: Zamboni D., Kruegel C. (eds) Recent Advances in Intrusion Detection. RAID 2006. Lecture Notes in Computer Science, vol 4219. Springer, Berlin, Heidelberg

Abstract

Defending a server against Internet worms and defending a user’s email inbox against spam bear certain similarities. In both cases, a stream of samples arrives, and a classifier must automatically determine whether each sample falls into a malicious target class (e.g., worm network traffic, or spam email). A learner typically generates a classifier automatically by analyzing two labeled training pools: one of innocuous samples, and one of samples that fall in the malicious target class.

Learning techniques have previously found success in settings where the content of the labeled samples used in training is either random, or even constructed by a helpful teacher, who aims to speed learning of an accurate classifier. In the case of learning classifiers for worms and spam, however, an adversary controls the content of the labeled samples to a great extent. In this paper, we describe practical attacks against learning, in which an adversary constructs labeled samples that, when used to train a learner, prevent or severely delay generation of an accurate classifier. We show that even a delusive adversary, whose samples are all correctly labeled, can obstruct learning. We simulate and implement highly effective instances of these attacks against the Polygraph [15] automatic polymorphic worm signature generation algorithms.

Keywords

automatic signature generation machine learning worm spam 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • James Newsome
    • 1
  • Brad Karp
    • 2
  • Dawn Song
    • 1
  1. 1.Carnegie Mellon University 
  2. 2.University College London