Abstract A Note on Methods for Explainable Malware Analysis

Martin Homola and Peter Anthony and Iveta Bečková and Ján
      Kľuka and Ján Mojžiš and Peter Švec and Štefan Balogh and Franco
      Alberto Cardillo and Franca Debole and Umberto Straccia and Martin
      Kenyeres and Francesco Giannini and Michelangelo Diligenti and
      Marco Gori and Tomáš Bisták and Daniel Trizna and Zekeri Adams

.
A Note on Methods for Explainable Malware Analysis.
In Proceedings of the Joint Ontology Workshops (JOWO) – Episode XI: The Sicilian Summer under the Etna, co-located with the 15th International Conference on Formal Ontology in Information Systems (FOIS 2025).

Abstract:
The inevitable rise of machine learning in malware analysis puts forward the need for human-understandable explanations of the learned results. We point out how the ontological representation of malware data provides
a suitable language for the construction of such explanations. We then focus on possible methods that enable producing such explanations and we reflect on our experience with them in the context of the EMBER dataset.