[adsense size='1']
How it Works
Malheur builds on the concept of dynamic analysis: Malware binaries are collected in the wild and executed in a sandbox, where their behavior is monitored during run-time. The execution of each malware binary results in a report of recorded behavior. Malheur analyzes these reports for discovery and discrimination of malware classes using machine learning.
Malheur can be applied to recorded behavior of various format, as long as monitored events are separated by delimiter symbols, for example as in reports generated by the popular malware sandboxes CWSandbox, Anubis, Norman Sandbox and Joebox.
Features
It supports four basic actions for analysis which can be applied to reports of recorded behavior:
[adsense size='1']
- Extraction of prototypes: From a given set of reports, malheur identifies a subset of prototypes representative for the full data set. The prototypes provide a quick overview of recorded behavior and can be used to guide manual inspection.
- Clustering of behavior: Malheur automatically identifies groups (clusters) of reports containing similar behavior. Clustering allows for discovering novel classes of malware and provides the basis for crafting specific detection and defense mechanisms, such as anti-virus signatures.
- Classification of behavior: Based on a set of previously clustered reports, malheur is able to assign unknown behavior to known groups of malware. Classification enables identifying novel and unknown variants of malware and can be used to filter program behavior prior to manual inspection.
- Incremental analysis: Malheur can be applied incrementally for analysis of large data sets. By processing reports in chunks, the run-time as well as memory requirements can be significantly reduced. This renders long-term application of malheur feasible, for example for daily analysis of incoming malware programs.
You can download Malheur 0.5.4 here:
Or read more here.
Gloss