Flow-Guided Mimicry Covert Communication over Learned Legitimate OFDM Signal Manifolds

Classical covert wireless communication is commonly formulated under a noise-only null hypothesis, in which a warden detects the presence of a transmission. In shared-spectrum settings with persistent legitimate traffic, however, a warden may already observe legitimate traffic and may therefore test whether an observation is statistically consistent with a legitimate signal class. Motivated by this regime, this paper studies mimicry covert communication in the post-demodulation OFDM resource-grid domain. A normalizing flow is trained on legitimate IEEE 802.11a NonHT-Data resource-grid observations, and covert bits are embedded by shared-key latent sign modulation, whose inner coordinatewise sign-flip rule preserves the standard Gaussian prior and thus the learned legitimate distribution under the ideal flow model. To improve message recovery under observation-domain perturbations, the framework further combines this inner embedding with a two-stage, two-state robustness-aware coordinate selector and a CRC-Polar outer code with reliability-weighted soft decoding. Experiments show that the coded design substantially improves message recovery over an uncoded repeated-sign baseline while keeping Willie-side discriminability low under both classifier-based and flow-density typicality tests. The study focuses on the learned post-demodulation resource-grid observation domain and leaves full over-the-air RF-chain validation for future work.