Combining a triplet autoencoder with DBSCAN centroid thresholds improves detection of unseen malware families in two datasets, but the temporal evaluation protocol and unreported hyperparameters undermine the results.
Towards open set deep networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Addressing malware family concept drift with triplet autoencoder
Combining a triplet autoencoder with DBSCAN centroid thresholds improves detection of unseen malware families in two datasets, but the temporal evaluation protocol and unreported hyperparameters undermine the results.