A transformer trained from scratch on simulated mixnet traffic exposes cumulative sender-message privacy erosion that per-message entropy and likelihood-difference metrics fail to capture.
MCMix: Anonymous Messaging via Secure Multiparty Computation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Quantifying Mix Network Privacy Erosion with Generative Models
A transformer trained from scratch on simulated mixnet traffic exposes cumulative sender-message privacy erosion that per-message entropy and likelihood-difference metrics fail to capture.