Speaker
Description
Malware analysis produces diverse information, ranging from static structural features to dynamic execution traces, including API calls, file-system modifications, registry changes, and network communications. Standards such as MAEC (Malware Attribute Enumeration and Characterization) and STIX (Structured Threat Information Expression) facilitate the representation and exchange of malware analysis results. However, their conceptual constructs do not always provide explicit semantic foundations or clearly distinguish between enduring entities and event-like entities. This lack of ontological distinction can lead to conceptual and representational mismatches, potentially hindering the consistent interpretation and integration of malware analysis information. To address these limitations, we present MAECO-Lite, a lightweight, UFO-grounded ontology for dynamic malware analysis. The ontology provides an ontologically grounded conceptualization of key dynamic malware analysis concepts and clarifies distinctions that are not sufficiently explicit in existing MAEC and STIX representations. We demonstrate its practical applicability through concept-learning experiments using DL-Learner, illustrating how it can support the automated learning of class expressions.
| Tlač postru/ Print poster | Budem požadovať tlač /I hereby required to print the poster in faculty |
|---|