Abstract
Malware reverse-engineering is an important type of analysis in cybersecurity. Rapidly identifying the tasks that a piece of malware is designed to perform is an important part of reverse engineering that is generally manually performed as it relies heavily on human intuition This paper describes how the use of cognitively-inspired inference can assist in automating some of malware task identification. Computational models derived from humaninspired inference were able to reach relatively higher asymptotic performance faster than traditional machine learning approaches such as decision trees and naïve Bayes classifiers. Using a real-world malware dataset, these cognitive models identified sets of tasks with an unbiased F1 measure of 0.94. Even when trained on historical datasets of malware samples from different families, the cognitive models still maintained the precision of decision tree and Bayes classifiers while providing a significant improvement to recall.
Original language | English (US) |
---|---|
Title of host publication | 24th Conference on Behavior Representation in Modeling and Simulation, BRiMS 2015, co-located with the International Social Computing, Behavioral Modeling and Prediction Conference, SBP 2015 |
Publisher | The BRIMS Society |
Pages | 18-25 |
Number of pages | 8 |
State | Published - 2015 |
Event | 24th Conference on Behavior Representation in Modeling and Simulation, BRiMS 2015, co-located with the International Social Computing, Behavioral Modeling and Prediction Conference, SBP 2015 - Washington, United States Duration: Mar 31 2015 → Apr 3 2015 |
Other
Other | 24th Conference on Behavior Representation in Modeling and Simulation, BRiMS 2015, co-located with the International Social Computing, Behavioral Modeling and Prediction Conference, SBP 2015 |
---|---|
Country/Territory | United States |
City | Washington |
Period | 3/31/15 → 4/3/15 |
Keywords
- Cognitive Architectures
- Functional Modeling
- Inference
- Instance-Based Learning
- Malware Analysis
ASJC Scopus subject areas
- Modeling and Simulation