Heterogeneous Graph Matching Networks
Preprint
Abstract
Information systems have widely been the target of malware attacks. Traditional signature-based malicious program detection algorithms can only detect known malware and are prone to evasion techniques such as binary obfuscation, while behavior-based approaches highly rely on the malware training samples and incur prohibitively high training cost. To address the limitations of existing techniques, we propose MatchGNet, a heterogeneous Graph Matching Network model to learn the graph representation and similarity metric simultaneously based on the invariant graph modeling of the program's execution behaviors. We conduct a systematic evaluation of our model and show that it is accurate in detecting malicious program behavior and can help detect malware attacks with less false positives. MatchGNet outperforms the state-of-the-art algorithms in malware detection by generating 50% less false positives while keeping zero false negatives.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Dynamic malware detection and phylogeny analysis using process miningInternational Journal of Information Security, 2018
- Modeling polypharmacy side effects with graph convolutional networksBioinformatics, 2018
- Burstiness of Intrusion Detection Process: Empirical Evidence and a Modeling ApproachIEEE Transactions on Information Forensics and Security, 2017
- MADAM: Effective and Efficient Behavior-based Android Malware Detection and PreventionIEEE Transactions on Dependable and Secure Computing, 2016
- A comparison of static, dynamic, and hybrid analysis for malware detectionJournal of Computer Virology and Hacking Techniques, 2015
- Learning to compare image patches via convolutional neural networks2015
- Malware Analysis with Tree Automata InferenceLecture Notes in Computer Science, 2011
- Fast Random Walk with Restart and Its ApplicationsIEEE International Conference on Data Mining (ICDM), 2006
- RASCAL: Calculation of Graph Similarity using Maximum Common Edge SubgraphsThe Computer Journal, 2002
- Chemical Similarity SearchingJournal of Chemical Information and Computer Sciences, 1998