FSK-encoded Dolphin audio is distinguishable from normal human speech via offline amplitude analysis: Dolphin's mean signal amplitude is 0.4 (std 224) versus 205 (std 1590) for natural speech — approximately an order of magnitude lower — enabling classification by a telecom operator who records calls. The paper also notes that standard CRC checksums appearing periodically every chunk provide a unique detectable signature if the adversary attempts to decode the audio.
From 2023-sharma-dolphin — Dolphin: A Cellular Voice Based Internet Shutdown Resistance System
· §6.5, Figs. 11–12
· 2023
· Privacy Enhancing Technologies
Implications
Superimpose FSK-encoded data onto a live human-speech audio track to match natural amplitude and frequency distributions, defeating amplitude-based offline classifiers.
Mask periodic integrity-check values (e.g., XOR CRC bytes with KDF-derived pseudorandom bytes) to remove the fixed-interval checksum signature that would otherwise fingerprint the protocol to an offline analyzer.