DASM: Domain-Aware Sharpness Minimization for Multi-Domain Voice Stream Steganalysis
For network security practitioners, DASM provides a robust steganalysis method that generalizes across diverse voice stream domains, addressing a critical bottleneck in practical deployment.
Existing network voice stream steganalysis methods fail to generalize across non-homologous data distributions due to sharp loss landscapes. The proposed DASM optimizer integrates domain-supervised contrastive learning with sharpness-aware minimization and adaptive domain gap modulation, outperforming state-of-the-art methods by a large margin in generalization and robustness.
The growing use of information hiding in network streaming media for covert communication poses a significant security threat, necessitating the development of robust detection technologies. However, existing steganalysis methods for network voice streams mostly rely on data distributions in specific scenarios, making it difficult to adapt to the practical detection needs of non-homologous data distributions. Through Hessian analysis, we find that the loss landscapes of mainstream models are dominated by numerous saddle points and sharp local minima, rendering them highly sensitive to data distribution shifts and fundamentally limiting generalization. Therefore, we propose a new optimizer, Domain-Aware Sharpness Minimization (DASM). The core mechanisms of DASM consist of two aspects: first, it integrates domain-supervised contrastive learning with sharpness-aware optimization, explicitly preserving inter-domain feature separation while seeking flat minima; second, we design an adaptive domain gap modulation strategy that dynamically calibrates the optimization loss weights by sensing the real-time feature separability of different domains. Extensive experimental results demonstrate that our method outperforms the state-of-the-art methods by a large margin and achieves excellent generalization and robustness.