DASM is a new optimizer that seeks flat minima while preserving inter-domain feature separation via contrastive learning and adaptive weighting for improved generalization in multi-domain voice stream steganalysis.
Detection of qim-based steganography in voip streams: A mobilevit-inspired model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DASM: Domain-Aware Sharpness Minimization for Multi-Domain Voice Stream Steganalysis
DASM is a new optimizer that seeks flat minima while preserving inter-domain feature separation via contrastive learning and adaptive weighting for improved generalization in multi-domain voice stream steganalysis.