Malware Family Discovery Using Reversible Jump MCMC Sampling of Regimes

Alexander D. Bolton*, Nicholas A. Heard

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)

1 Citation (Scopus)

Abstract

Malware is computer software that has either been designed or modified with malicious intent. Hundreds of thousands of new malware threats appear on the internet each day. This is made possible through reuse of known exploits in computer systems that have not been fully eradicated; existing pieces of malware can be trivially modified and combined to create new malware, which is unknown to anti-virus programs. Finding new software with similarities to known malware is therefore an important goal in cyber-security. A dynamic instruction trace of a piece of software is the sequence of machine language instructions it generates when executed. Statistical analysis of a dynamic instruction trace can help reverse engineers infer the purpose and origin of the software that generated it. Instruction traces have been successfully modeled as simple Markov chains, but empirically there are change points in the structure of the traces, with recurring regimes of transition patterns. Here, reversible jump Markov chain Monte Carlo for change point detection is extended to incorporate regime-switching, allowing regimes to be inferred from malware instruction traces. A similarity measure for malware programs based on regime matching is then used to infer the originating families, leading to compelling performance results.

Original languageEnglish
Number of pages13
JournalJournal of the American Statistical Association
Early online date11 Jul 2018
DOIs
Publication statusE-pub ahead of print - 11 Jul 2018

Keywords

  • Change point analysis
  • Dynamic instruction trace
  • Regime-switching
  • Reversible jump Markov chain Monte Carlo

Fingerprint Dive into the research topics of 'Malware Family Discovery Using Reversible Jump MCMC Sampling of Regimes'. Together they form a unique fingerprint.

  • Cite this